Paper Citation Record · LEDGER

Open Problems in Mechanistic Interpretability

As of 10 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 100 inbound Pith citation observations for arXiv:2501.16496.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2501.16496 v1

Coverage vector

measured 77 of 77 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z

measured 177 of 177 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 100 of 102 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:55:02.232925Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

77 of 77 outbound references displayed

verified exact8
verified fuzzy45
unresolved16
parse uncertain0
malformed identifier1
metadata mismatch7

External citation measurements

5
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation c923f1b3-d1fb-44db-bf56-0754c2c8918b · outbound

This paper cites a is b” fail to learn “b is a.

Open Problems in Mechanistic Interpretability a is b” fail to learn “b is a

Reference 1

Resolution: verified exact; doi, observed 2026-05-14T18:30:06.027122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7354f512-55a5-4d67-9115-d2a6c561d750 · outbound

This paper cites https://distill.pub/2019/activation-atlas.

Open Problems in Mechanistic Interpretability https://distill.pub/2019/activation-atlas

Reference 2

Resolution: verified exact; doi, observed 2026-05-14T18:30:05.975539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4fadc288-2e14-48ae-a8f7-9d68faa121d4 · outbound

This paper cites Transactions of the Association for Computational Linguistics9, 160–175 (2021).

Open Problems in Mechanistic Interpretability Transactions of the Association for Computational Linguistics9, 160–175 (2021)

Reference 3

Resolution: metadata mismatch; doi, observed 2026-05-14T18:30:05.981712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ce5c2ddc-2cd2-446f-aac3-3ad238d49f20 · outbound

This paper cites In: Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, RepE- val@ACL 2016, Berlin, Germany, August 2016.

Open Problems in Mechanistic Interpretability In: Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, RepE- val@ACL 2016, Berlin, Germany, August 2016

Reference 4

Resolution: verified exact; doi, observed 2026-05-14T18:30:05.986398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 71ac7d6e-65b9-481e-b224-208d9e84bcbd · outbound

This paper cites News from Generative Artificial Intelligence Is Believed Less.

Open Problems in Mechanistic Interpretability News from Generative Artificial Intelligence Is Believed Less

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:05.992913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bc772c23-b7a3-4894-8ca1-5a6433b0f8ab · outbound

This paper cites A Structural Probe for Finding Syntax in Word Representations.

Open Problems in Mechanistic Interpretability A Structural Probe for Finding Syntax in Word Representations

Reference 6

Resolution: metadata mismatch; doi, observed 2026-05-14T18:30:05.997680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 180db348-902e-4fbc-9ed3-0f0f732c27d9 · outbound

This paper cites Backward Lens: Pro- jecting Language Model Gradients into the Vocabulary Space.

Open Problems in Mechanistic Interpretability Backward Lens: Pro- jecting Language Model Gradients into the Vocabulary Space

Reference 7

Resolution: verified exact; doi, observed 2026-05-14T18:30:06.002546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 876af1f0-0ae5-4f45-a4d1-626a50d64d18 · outbound

This paper cites Understanding Deep Image Representations by Inverting Them.

Open Problems in Mechanistic Interpretability Understanding Deep Image Representations by Inverting Them

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-14T18:30:06.009807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e6c5ae18-3944-4aa7-b2f4-d55cf0c6692f · outbound

This paper cites URL https://distill.

Open Problems in Mechanistic Interpretability URL https://distill

Reference 9

Resolution: verified exact; doi, observed 2026-05-14T18:30:06.016148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7861a7dd-40ac-4ba7-b676-e12f1258afe4 · outbound

This paper cites Does Transformer Interpretability Transfer to RNNs?.

Open Problems in Mechanistic Interpretability Does Transformer Interpretability Transfer to RNNs?

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.053221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 20d8ff8f-dcdc-44d5-b6fe-d6e676ea4ca5 · outbound

This paper cites Weight-based Decomposition: A Case for Bilinear MLPs.

Open Problems in Mechanistic Interpretability Weight-based Decomposition: A Case for Bilinear MLPs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.059231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 733c560a-3e06-47fb-b145-26325ebdae61 · outbound

This paper cites Jorge Pérez, Javier Marinkovi ´c, and Pablo Barceló.

Open Problems in Mechanistic Interpretability Jorge Pérez, Javier Marinkovi ´c, and Pablo Barceló

Reference 12

Resolution: metadata mismatch; doi, observed 2026-05-14T18:30:06.031452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 70f8a027-b816-4dcb-b739-657179aa7612 · outbound

This paper cites Dynamic models of large-scale brain activity.

Open Problems in Mechanistic Interpretability Dynamic models of large-scale brain activity

Reference 13

Resolution: malformed identifier; doi_truncated, observed 2026-05-14T18:30:06.036048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ed55669f-b1a4-48aa-8426-aafe99b3f707 · outbound

This paper cites why should i trust you?.

Open Problems in Mechanistic Interpretability why should i trust you?

Reference 14

Resolution: verified exact; doi, observed 2026-05-14T18:30:06.040799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 070cb7c8-af62-4070-8a51-0c1eda90f730 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Open Problems in Mechanistic Interpretability Gemini: A Family of Highly Capable Multimodal Models

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-05-14T18:30:06.046857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f996f9eb-11eb-4278-843d-81c8ac638337 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Open Problems in Mechanistic Interpretability Representation Engineering: A Top-Down Approach to AI Transparency

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-14T18:30:06.022244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 54952ac5-de83-4b8c-a063-a89db4407a75 · outbound

This paper cites What isomorphism or what approximation of a neural network (or parts of it) is the best way to express it for the purposes of interpreting it? b.

Open Problems in Mechanistic Interpretability What isomorphism or what approximation of a neural network (or parts of it) is the best way to express it for the purposes of interpreting it? b

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.280695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation da960d65-d177-4de4-9691-917c2db17768 · outbound

This paper cites To what extent do models encode concepts linearly in their representations? b.

Open Problems in Mechanistic Interpretability To what extent do models encode concepts linearly in their representations? b

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.285689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7142ca1c-dfb2-4d16-a8de-fde20845a135 · outbound

This paper cites Can we fully determine the causes of feature superposition and polysemanticity within neural networks? b.

Open Problems in Mechanistic Interpretability Can we fully determine the causes of feature superposition and polysemanticity within neural networks? b

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.290636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d58e9275-d820-483a-9da2-2f3143118ea8 · outbound

This paper cites What lies in SDL reconstruction errors? Will the errors converge to zero with methodological progress? b.

Open Problems in Mechanistic Interpretability What lies in SDL reconstruction errors? Will the errors converge to zero with methodological progress? b

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.296069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a2319578-15f4-401b-bac8-e2c4337e0c99 · outbound

This paper cites How can we identify the underlying functional structure of networks (which defines why acti- vations are located in particular geometric arrangements in activation space)? 75 b.

Open Problems in Mechanistic Interpretability How can we identify the underlying functional structure of networks (which defines why acti- vations are located in particular geometric arrangements in activation space)? 75 b

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.300906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8d551ff8-d059-43de-b77e-ffff049af662 · outbound

This paper cites Can we distinguish parts of networks that underlie generalization from parts that underlie memorization? b.

Open Problems in Mechanistic Interpretability Can we distinguish parts of networks that underlie generalization from parts that underlie memorization? b

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.305547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 36d6b044-49c1-4eb6-80f3-1e6deba5f818 · outbound

This paper cites Interpretability training: Can we train networks that are interpretable by default at low per- formance cost? b.

Open Problems in Mechanistic Interpretability Interpretability training: Can we train networks that are interpretable by default at low per- formance cost? b

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.310467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ff490481-0010-4bed-bd44-30fa7397fec4 · outbound

This paper cites How can we avoid imposing human bias to explanations? b.

Open Problems in Mechanistic Interpretability How can we avoid imposing human bias to explanations? b

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.315126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9e7a2ef4-9d63-44c9-a977-cedc8afe1475 · outbound

This paper cites How can we develop attribution methods that capture higher-order effects beyond first-order approximations of model behavior? b.

Open Problems in Mechanistic Interpretability How can we develop attribution methods that capture higher-order effects beyond first-order approximations of model behavior? b

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.319803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f48a12fc-9794-471d-9c2b-792212f06c56 · outbound

This paper cites Hydra effect.

Open Problems in Mechanistic Interpretability Hydra effect

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.323908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fd6a03bd-378f-4e78-89f1-3f6e4a18d578 · outbound

This paper cites Can we improve on methodologies for evaluating hypotheses through their predictive power on activations of network components? 76 b.

Open Problems in Mechanistic Interpretability Can we improve on methodologies for evaluating hypotheses through their predictive power on activations of network components? 76 b

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.329061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dd7c3def-47e8-4f2e-bb90-b3d64c780245 · outbound

This paper cites model organisms.

Open Problems in Mechanistic Interpretability model organisms

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.333830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 14e69a69-563f-4137-8d83-523996405b29 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.338193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f398f711-81c7-4a32-8a75-d7607e710b0d · outbound

This paper cites stress tests.

Open Problems in Mechanistic Interpretability stress tests

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.342427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5755e2ed-f3ec-4928-9301-fafb589f72b5 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.346926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d09aa42-1993-4b2d-b114-1e85c75fbec5 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.063177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 78a8fd19-d816-4ed1-b2d3-11a009d9c3d4 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.067203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 922da718-ba11-4302-a220-746b459bc974 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.070676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 11234bc9-0d64-4d71-9d7f-4beef967e464 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.074272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b50fc385-f7fe-48be-8db6-451b216e4dff · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.078001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 637940f9-a503-4482-90cb-3e5c80dc51a3 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.082145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aa50ed94-92f6-427e-8162-4156ae230790 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.086866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8bf28823-4860-44f1-84e3-35126cae0eb5 · outbound

This paper cites Through automating the generation and testing of arbitrary hypotheses? b.

Open Problems in Mechanistic Interpretability Through automating the generation and testing of arbitrary hypotheses? b

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.091151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0ded2bb9-d480-4386-aca4-edd1ff675b13 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.095248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 52823d66-ce85-4cc0-b820-d9af4f453ed1 · outbound

This paper cites Conceptual interpretability research? b.

Open Problems in Mechanistic Interpretability Conceptual interpretability research? b

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.099447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c3a19264-694e-4037-a5b4-474e804a300f · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.103730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9ecbcb60-0529-4e4c-a37d-a64ba61aba85 · outbound

This paper cites white box.

Open Problems in Mechanistic Interpretability white box

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.108001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 31489b22-e6cb-461c-a85a-8a970a972393 · outbound

This paper cites Can we use interpretability insights to make red-teaming more efficient than current methods? b.

Open Problems in Mechanistic Interpretability Can we use interpretability insights to make red-teaming more efficient than current methods? b

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.112199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f13ced3f-1e9e-4445-be0b-8dc8c21ce751 · outbound

This paper cites Can we get mechanistic anomaly detection to work? b.

Open Problems in Mechanistic Interpretability Can we get mechanistic anomaly detection to work? b

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.116859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0f10da81-f714-4635-b378-ae44210a6ada · outbound

This paper cites How can we make activation steering more precise and reduce its side effects? b.

Open Problems in Mechanistic Interpretability How can we make activation steering more precise and reduce its side effects? b

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.121134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8b6d10ce-c5c2-4d7a-bf3e-aa3687922b73 · outbound

This paper cites Will carving the network at its true joints help us improve on model unlearning and editing? b.

Open Problems in Mechanistic Interpretability Will carving the network at its true joints help us improve on model unlearning and editing? b

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.125782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e6a5ebc1-2fab-4852-b5b2-bd4e527cb3d3 · outbound

This paper cites Can we make finetuning more sample-efficient by targeting specific parameters? b.

Open Problems in Mechanistic Interpretability Can we make finetuning more sample-efficient by targeting specific parameters? b

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.130380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f5db5b02-b6a8-48cf-b942-2c704909d5a9 · outbound

This paper cites values” or “goals.

Open Problems in Mechanistic Interpretability values” or “goals

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.134966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2a194e14-6273-4935-a009-8d463633ad6d · outbound

This paper cites Can current toy model verification approaches scale to frontier systems? b.

Open Problems in Mechanistic Interpretability Can current toy model verification approaches scale to frontier systems? b

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.139686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fa1f6919-6fdf-4a9a-89e5-a397efe4dd9a · outbound

This paper cites enumerative safety.

Open Problems in Mechanistic Interpretability enumerative safety

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.144570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 728fdd09-3a9b-42b8-a986-10b2fb668575 · outbound

This paper cites Can we identify early signatures that predict emergent capabilities? b.

Open Problems in Mechanistic Interpretability Can we identify early signatures that predict emergent capabilities? b

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.149503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6b570a64-7e75-431d-9ed9-27766a82bba9 · outbound

This paper cites How do specific training examples influence the development of model mechanisms? b.

Open Problems in Mechanistic Interpretability How do specific training examples influence the development of model mechanisms? b

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.154069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 13bb5b87-ec8d-4a56-9fca-436aca87e015 · outbound

This paper cites How can we identify capabilities that could be ‘unlocked’ through prompting or finetuning? b.

Open Problems in Mechanistic Interpretability How can we identify capabilities that could be ‘unlocked’ through prompting or finetuning? b

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.159176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37a55358-fc99-42e2-a397-27f2d166fddb · outbound

This paper cites How can we identify skippable computations without affecting outputs? b.

Open Problems in Mechanistic Interpretability How can we identify skippable computations without affecting outputs? b

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.164006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8b60cb08-2fab-496f-8d13-6a95b5940da0 · outbound

This paper cites Can we better select training data by understanding example influence? b.

Open Problems in Mechanistic Interpretability Can we better select training data by understanding example influence? b

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.168949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c7249d5b-baab-4110-aa85-0493b5c0c1b0 · outbound

This paper cites Can we design better inductive biases based on mechanistic insights? b.

Open Problems in Mechanistic Interpretability Can we design better inductive biases based on mechanistic insights? b

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.173860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f4d30f0b-e153-498a-b3d3-3ade9cc32070 · outbound

This paper cites How can we extract novel patterns and predictors that models have found? b.

Open Problems in Mechanistic Interpretability How can we extract novel patterns and predictors that models have found? b

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.178610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c8b34bf7-027d-47e8-bd4a-a014a73240a9 · outbound

This paper cites How can we detect when models have found genuinely novel patterns? b.

Open Problems in Mechanistic Interpretability How can we detect when models have found genuinely novel patterns? b

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.183194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 33032b8d-fdb0-466b-b15d-49507245f6df · outbound

This paper cites Do current interpretability methods (SDL, circuit analysis) transfer to SSMs? Or, like the transition from CNNs to transformers, are new approaches necessary? b.

Open Problems in Mechanistic Interpretability Do current interpretability methods (SDL, circuit analysis) transfer to SSMs? Or, like the transition from CNNs to transformers, are new approaches necessary? b

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.188174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 69a1577f-00cd-4909-9ec1-89990f4a40b1 · outbound

This paper cites universality hypothesis.

Open Problems in Mechanistic Interpretability universality hypothesis

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.192701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4e14c264-7a9e-4bce-8376-98e1ac11da50 · outbound

This paper cites How can we prepare for interpreting novel architectures? b.

Open Problems in Mechanistic Interpretability How can we prepare for interpreting novel architectures? b

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.197493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c22ca0a1-8991-4a95-9a91-e92da7086776 · outbound

This paper cites How can we visualize model internals in an intuitive way? b.

Open Problems in Mechanistic Interpretability How can we visualize model internals in an intuitive way? b

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.202163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 82fb5570-d563-41fe-88ef-ba5c209fc2a3 · outbound

This paper cites How can we help auditors find potential failure modes directly? b.

Open Problems in Mechanistic Interpretability How can we help auditors find potential failure modes directly? b

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.206840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f436bcc4-edee-4330-beb8-e88787400224 · outbound

This paper cites How can transparency features help users calibrate trust? b.

Open Problems in Mechanistic Interpretability How can transparency features help users calibrate trust? b

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.211425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0d343568-e0b4-45fa-8cf9-4d0c8cdc4f94 · outbound

This paper cites Can we identify specific mechanisms that caused AI failures? b.

Open Problems in Mechanistic Interpretability Can we identify specific mechanisms that caused AI failures? b

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.216371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 82df408c-34da-491c-b04a-a1ac5813ebbf · outbound

This paper cites Can we identify mechanisms responsible for specific dangerous capabilities? b.

Open Problems in Mechanistic Interpretability Can we identify mechanisms responsible for specific dangerous capabilities? b

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.220973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d8058ef9-d43e-4b2b-9631-ea40fe3ceee4 · outbound

This paper cites How can we trace decision mechanisms to explain model outputs? b.

Open Problems in Mechanistic Interpretability How can we trace decision mechanisms to explain model outputs? b

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.225663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bc0c733c-5cbb-4c36-b777-d2b2dcbec6c3 · outbound

This paper cites How can we use interpretability to improve capability elicitation? b.

Open Problems in Mechanistic Interpretability How can we use interpretability to improve capability elicitation? b

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.230699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f2b53f9b-7b37-4726-9e0c-6494fb436bb7 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.235543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 206c09bb-3a8c-48d7-94ba-404764a8ce0c · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.241536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3809b625-05f9-48e9-8ca7-ce838f0fa2e8 · outbound

This paper cites Can we use interpretability to construct reliable test-time monitors to detect AI incidents? b.

Open Problems in Mechanistic Interpretability Can we use interpretability to construct reliable test-time monitors to detect AI incidents? b

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.246817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ac916f48-a562-4c95-8c4e-9a524698ab0a · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.251798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 10336af0-81e7-4135-b1ee-ddffd0bd86e8 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.258796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 874cc514-7cfe-4dde-a966-281ce07afc48 · outbound

This paper cites an unresolved cited work.

Open Problems in Mechanistic Interpretability Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-05-14T18:30:06.264148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0ef76cd7-ad95-446a-9abc-d601c6cc535e · outbound

This paper cites What are the goals of the field? b.

Open Problems in Mechanistic Interpretability What are the goals of the field? b

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.269607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0594a943-fa8a-4b6e-9744-2a116cc5c8cb · outbound

This paper cites How can we communicate the results of our research such that the risk of their misuse is minimized? 82.

Open Problems in Mechanistic Interpretability How can we communicate the results of our research such that the risk of their misuse is minimized? 82

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T18:30:06.275564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 5d1fdc47-bc03-46b5-b430-4f90cb9c1ea1 · inbound

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition cites this paper.

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Open Problems in Mechanistic Interpretability

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-10T14:55:02.232925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75c4e53e-9a54-450a-a2fb-d33a00ac8c4b · inbound

Low-Rank Adapting Models for Sparse Autoencoders cites this paper.

Low-Rank Adapting Models for Sparse Autoencoders Open Problems in Mechanistic Interpretability

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-09T20:18:31.107491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 190ff932-4df3-4855-b830-d3c10bd7b4d1 · inbound

Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives cites this paper.

Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives Open Problems in Mechanistic Interpretability

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-09T11:29:21.292467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9da5522c-3365-4982-b9da-49247b4c1bf2 · inbound

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation cites this paper.

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation Open Problems in Mechanistic Interpretability

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-08T19:15:55.034232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5ab5823-34e2-4239-b5eb-d2abb76398a7 · inbound

(How) Can Transformers Predict Pseudo-Random Numbers? cites this paper.

(How) Can Transformers Predict Pseudo-Random Numbers? Open Problems in Mechanistic Interpretability

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T18:32:14.806991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d25d3c-4e7f-4c85-a8bf-1e781629354c · inbound

Explaining Neural Networks with Reasons cites this paper.

Explaining Neural Networks with Reasons Open Problems in Mechanistic Interpretability

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:42:42.738291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71ef92c-986b-492d-bf4c-c50c5a7a7587 · inbound

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering cites this paper.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Open Problems in Mechanistic Interpretability

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.825428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3da134b9-22d9-4cf2-a558-34b803115ff3 · inbound

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models cites this paper.

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models Open Problems in Mechanistic Interpretability

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:43.200839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30b1ff91-1129-4565-af17-7658331d90a5 · inbound

Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks cites this paper.

Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks Open Problems in Mechanistic Interpretability

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:54.459356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4591e58e-693c-4a8d-b7f6-dc5599d4d472 · inbound

How Do Transformers Learn Variable Binding in Symbolic Programs? cites this paper.

How Do Transformers Learn Variable Binding in Symbolic Programs? Open Problems in Mechanistic Interpretability

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:50:09.978542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44b7442f-32c0-4d6c-94e5-e38f4619f4be · inbound

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling cites this paper.

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling Open Problems in Mechanistic Interpretability

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:57.279860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f85038-48b3-4789-9cad-ea89136df48a · inbound

Sparsification and Reconstruction from the Perspective of Representation Geometry cites this paper.

Sparsification and Reconstruction from the Perspective of Representation Geometry Open Problems in Mechanistic Interpretability

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:11:09.340402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 919f7776-77bc-4d98-9e36-159147c403cf · inbound

Zero-Shot Vision Encoder Grafting via LLM Surrogates cites this paper.

Zero-Shot Vision Encoder Grafting via LLM Surrogates Open Problems in Mechanistic Interpretability

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:09.455799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4fccfa1-52b1-4557-94cb-cab9a1e8d023 · inbound

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval cites this paper.

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval Open Problems in Mechanistic Interpretability

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:00.227957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e8a247d-628d-4423-89f8-812a38e492f9 · inbound

Risks of AI-driven product development and strategies for their mitigation cites this paper.

Risks of AI-driven product development and strategies for their mitigation Open Problems in Mechanistic Interpretability

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:09:58.250420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c918ca0-37ad-4364-b348-98a8cb82979e · inbound

Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey cites this paper.

Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey Open Problems in Mechanistic Interpretability

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T10:46:20.241685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29a830c7-73c5-455f-b948-c73a26e39bb3 · inbound

On the Fundamental Impossibility of Hallucination Control in Large Language Models cites this paper.

On the Fundamental Impossibility of Hallucination Control in Large Language Models Open Problems in Mechanistic Interpretability

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T10:46:54.785925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47020588-307b-4faa-a301-657d98bd9649 · inbound

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models cites this paper.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Open Problems in Mechanistic Interpretability

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.860460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ecaa4c-e899-43b5-925b-20aa394b7bd5 · inbound

How Visual Representations Map to Language Feature Space in Multimodal LLMs cites this paper.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Open Problems in Mechanistic Interpretability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:07.977614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5584384c-eafb-41cf-9f8c-642c945093dd · inbound

Because we have LLMs, we Can and Should Pursue Agentic Interpretability cites this paper.

Because we have LLMs, we Can and Should Pursue Agentic Interpretability Open Problems in Mechanistic Interpretability

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T01:03:21.495743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40e474c2-869f-4a60-8bac-dba478f0581b · inbound

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) cites this paper.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Open Problems in Mechanistic Interpretability

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:26:57.320407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aedf96a0-5269-409e-a0c7-9c25cfb7b7f0 · inbound

Mechanistic Interpretability Needs Philosophy cites this paper.

Mechanistic Interpretability Needs Philosophy Open Problems in Mechanistic Interpretability

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-21T23:50:47.297873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c51c0ec3-ae89-4f7d-9ea1-328ace5d5dc0 · inbound

Stochastic Parameter Decomposition cites this paper.

Stochastic Parameter Decomposition Open Problems in Mechanistic Interpretability

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T22:48:38.733150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dd42544-8ad2-47ff-8e75-92947e5ea738 · inbound

Position: Use Sparse Autoencoders to Discover Unknowns cites this paper.

Position: Use Sparse Autoencoders to Discover Unknowns Open Problems in Mechanistic Interpretability

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:33.494081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb795f77-cfc4-436b-8d93-9af6e3b3d8d9 · inbound

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence cites this paper.

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence Open Problems in Mechanistic Interpretability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:15.531365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 414bdef2-d59a-4fa1-b464-57ccf9deb578 · inbound

CytoSAE: Interpretable Cell Embeddings for Hematology cites this paper.

CytoSAE: Interpretable Cell Embeddings for Hematology Open Problems in Mechanistic Interpretability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:54.104626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65d59515-c219-40fd-b934-1b5d17cd9996 · inbound

Task complexity shapes internal representations and robustness in neural networks cites this paper.

Task complexity shapes internal representations and robustness in neural networks Open Problems in Mechanistic Interpretability

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:51:54.745952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1127dc0b-0c0f-49ac-b1f8-90151723e9e8 · inbound

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns cites this paper.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Open Problems in Mechanistic Interpretability

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.956496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 486e437e-19bd-4800-bbea-32c5ed1fca99 · inbound

SATORI: Static Test Oracle Generation for REST APIs cites this paper.

SATORI: Static Test Oracle Generation for REST APIs Open Problems in Mechanistic Interpretability

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T17:26:48.632505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a00a0626-d2ba-46e1-a2c7-2d14dcd321c4 · inbound

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation cites this paper.

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation Open Problems in Mechanistic Interpretability

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-05T18:47:45.332785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa04eb6-b3bc-42af-97a7-eff4940835a2 · inbound

Challenges in Understanding Modality Conflict in Vision-Language Models cites this paper.

Challenges in Understanding Modality Conflict in Vision-Language Models Open Problems in Mechanistic Interpretability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T11:26:17.847288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9feca2dc-b196-4eed-918f-dcdc12b219cf · inbound

\texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World cites this paper.

\texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World Open Problems in Mechanistic Interpretability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T23:10:46.324925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46dd83e5-81b7-4785-8c23-1c4a5d7ea856 · inbound

We Need a New Ethics for a World of AI Agents cites this paper.

We Need a New Ethics for a World of AI Agents Open Problems in Mechanistic Interpretability

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T18:01:02.649733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dd62860-9d42-4914-b4ac-67e3bdb9673a · inbound

Do Activation Verbalization Methods Convey Privileged Information? cites this paper.

Do Activation Verbalization Methods Convey Privileged Information? Open Problems in Mechanistic Interpretability

Reference 47

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T15:42:42.156296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3973880d-2d93-49e7-8241-a9134b7803b1 · inbound

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack cites this paper.

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack Open Problems in Mechanistic Interpretability

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T13:06:23.426950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fe01834c-621b-426b-ad2f-964f424cf967 · inbound

Feature Identification via the Empirical NTK cites this paper.

Feature Identification via the Empirical NTK Open Problems in Mechanistic Interpretability

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:01:16.935370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation afa98fb5-78dd-4682-82bf-0106ea6ebe34 · inbound

Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling cites this paper.

Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling Open Problems in Mechanistic Interpretability

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-18T10:41:16.005714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8be092f4-4e0d-48bb-813f-c95844dc4543 · inbound

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary cites this paper.

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary Open Problems in Mechanistic Interpretability

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T13:24:53.325174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6894c222-62fd-4f54-8a11-30e74d357a9e · inbound

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary cites this paper.

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary Open Problems in Mechanistic Interpretability

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T13:24:53.065282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 49e5798c-ace3-4197-a9c7-2e6038316587 · inbound

Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations cites this paper.

Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations Open Problems in Mechanistic Interpretability

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T09:08:54.672241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69af4bca-e6f9-4c18-a824-b6177d61e9a6 · inbound

Some economics of artificial superintelligence cites this paper.

Some economics of artificial superintelligence Open Problems in Mechanistic Interpretability

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T23:18:42.819258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aca47b11-2890-4de7-8d0e-993852cd1ac5 · inbound

Internal Deployment in the AI Act cites this paper.

Internal Deployment in the AI Act Open Problems in Mechanistic Interpretability

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T17:54:18.538252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d610a1c0-cf66-4de5-b807-533ef22ec407 · inbound

Singular Vectors of Attention Heads Align with Features cites this paper.

Singular Vectors of Attention Heads Align with Features Open Problems in Mechanistic Interpretability

Reference 1972

Resolution: unresolved; no resolver link, observed 2026-08-02T23:38:14.568953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90b20a3c-93e6-4d89-888e-f2b6e3d23fb4 · inbound

Transformers converge to invariant algorithmic cores cites this paper.

Transformers converge to invariant algorithmic cores Open Problems in Mechanistic Interpretability

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T20:46:29.019024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 327b16b1-7168-42ea-a292-e4ebbb6c1b41 · inbound

Steering at the Source: Style Modulation Heads for Robust Persona Control cites this paper.

Steering at the Source: Style Modulation Heads for Robust Persona Control Open Problems in Mechanistic Interpretability

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T21:21:26.170990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50faadc7-4624-4cf7-9ec9-c6c7d9942b90 · inbound

Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space cites this paper.

Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space Open Problems in Mechanistic Interpretability

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d2337bd9-2222-4d26-8495-b65ad970e9af · inbound

The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts cites this paper.

The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts Open Problems in Mechanistic Interpretability

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 99127db3-ebd8-4dd4-8844-f2479e024303 · inbound

The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts cites this paper.

The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts Open Problems in Mechanistic Interpretability

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9c48241c-24be-43f4-b282-22e72fd9de63 · inbound

Functional Similarity Metric for Neural Networks: Overcoming Parametric Ambiguity via Activation Region Analysis cites this paper.

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fdad4d2b-6a09-4abb-a7e6-0ed2e1d0bc0c · inbound

Diverse Dictionary Learning cites this paper.

Diverse Dictionary Learning Open Problems in Mechanistic Interpretability

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 602ab21c-a12c-45c1-bf27-2de8195f388b · inbound

Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety cites this paper.

Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety Open Problems in Mechanistic Interpretability

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a98b13c9-7ceb-4c25-8ef4-53b34d117048 · inbound

Understanding the Mechanism of Altruism in Large Language Models cites this paper.

Understanding the Mechanism of Altruism in Large Language Models Open Problems in Mechanistic Interpretability

Reference 230

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f898cbd0-13be-4004-9f07-cb2d2b90f160 · inbound

There Will Be a Scientific Theory of Deep Learning cites this paper.

There Will Be a Scientific Theory of Deep Learning Open Problems in Mechanistic Interpretability

Reference 164

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8d03db4a-339b-41fd-9ec3-1604d377aff2 · inbound

Compared to What? Baselines and Metrics for Counterfactual Prompting cites this paper.

Compared to What? Baselines and Metrics for Counterfactual Prompting Open Problems in Mechanistic Interpretability

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b176c6a8-7299-4588-afea-58e6699bcce2 · inbound

Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts cites this paper.

Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts Open Problems in Mechanistic Interpretability

Reference 84

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fc33ff26-dc31-4f7c-9083-1c53c39ec565 · inbound

Linear-Readout Floors and Threshold Recovery in Computation in Superposition cites this paper.

Linear-Readout Floors and Threshold Recovery in Computation in Superposition Open Problems in Mechanistic Interpretability

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3f373b76-6617-469a-84b1-b2b6b46973fd · inbound

What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis cites this paper.

What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis Open Problems in Mechanistic Interpretability

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1ec700c8-2b4d-449a-a155-81d2976a55f3 · inbound

High-Dimensional Statistics: Reflections on Progress and Open Problems cites this paper.

High-Dimensional Statistics: Reflections on Progress and Open Problems Open Problems in Mechanistic Interpretability

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6d6162f0-68f5-41c0-b5b5-238ac11a8d83 · inbound

High-Dimensional Statistics: Reflections on Progress and Open Problems cites this paper.

High-Dimensional Statistics: Reflections on Progress and Open Problems Open Problems in Mechanistic Interpretability

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-06-30T23:35:07.981613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4d72dd99-4ea6-407e-a315-744b1ea3a925 · inbound

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior cites this paper.

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior Open Problems in Mechanistic Interpretability

Reference 80

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1554ce28-e0c3-4fd1-a1f7-e3ac49780471 · inbound

Bilinear autoencoders find interpretable manifolds cites this paper.

Bilinear autoencoders find interpretable manifolds Open Problems in Mechanistic Interpretability

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0d33df20-8fa4-4df4-a30d-a013c45da974 · inbound

From Mechanistic to Compositional Interpretability cites this paper.

From Mechanistic to Compositional Interpretability Open Problems in Mechanistic Interpretability

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ebcc1c64-06cd-4f63-8baa-fd9145dc60d2 · inbound

Do Linear Probes Generalize Better in Persona Coordinates? cites this paper.

Do Linear Probes Generalize Better in Persona Coordinates? Open Problems in Mechanistic Interpretability

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0d44401a-0fe5-4f4f-8d5b-8f57e2d138bb · inbound

Do Linear Probes Generalize Better in Persona Coordinates? cites this paper.

Do Linear Probes Generalize Better in Persona Coordinates? Open Problems in Mechanistic Interpretability

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-19T17:07:40.471481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 35e42c23-a4a1-4037-98de-8da6505aa50a · inbound

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery cites this paper.

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery Open Problems in Mechanistic Interpretability

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 20a61b1d-76e3-4180-bebd-16a5a2a48517 · inbound

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models cites this paper.

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models Open Problems in Mechanistic Interpretability

Reference 63

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 82a9a522-b342-4779-960f-0947f5b1bd04 · inbound

Metaphor Is Not All Attention Needs cites this paper.

Metaphor Is Not All Attention Needs Open Problems in Mechanistic Interpretability

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a016c9a3-61bc-4973-8d54-32712ddabde8 · inbound

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space cites this paper.

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space Open Problems in Mechanistic Interpretability

Reference 128

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T18:30:06.348607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 97721bca-9435-45d4-87fd-e19266247cc5 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Open Problems in Mechanistic Interpretability

Reference 68

Resolution: metadata mismatch; local_arxiv, observed 2026-05-14T20:59:28.715619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3dcb8d84-c08f-4b65-a915-38604c7543ac · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Open Problems in Mechanistic Interpretability

Reference 68

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T04:59:45.052674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 57a03569-8ab6-4e6c-a037-ed4b5c2a5616 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Open Problems in Mechanistic Interpretability

Reference 68

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T21:53:47.195232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 83788547-003f-413a-a697-dc1896affb6b · inbound

Tracing Persona Vectors Through LLM Pretraining cites this paper.

Tracing Persona Vectors Through LLM Pretraining Open Problems in Mechanistic Interpretability

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-14T20:29:27.899540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 896c9ec7-051e-4b98-af56-eef1f043f7c3 · inbound

Explainable AI Isn't Enough! Rethinking Algorithmic Contestability cites this paper.

Explainable AI Isn't Enough! Rethinking Algorithmic Contestability Open Problems in Mechanistic Interpretability

Reference 46

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T19:12:43.807569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 28fdf147-299c-479d-9c97-ea8bffb1e399 · inbound

Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System cites this paper.

Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System Open Problems in Mechanistic Interpretability

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-21T06:59:45.603518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5e5cc594-e20c-4b20-b906-73920776928a · inbound

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift cites this paper.

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift Open Problems in Mechanistic Interpretability

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:16:16.110708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5f1e45e0-bde3-4f0b-816f-c2a5a2ebd8ee · inbound

Disentanglement Beyond Generative Models with Riemannian ICA cites this paper.

Disentanglement Beyond Generative Models with Riemannian ICA Open Problems in Mechanistic Interpretability

Reference 76

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:51:15.997118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5f0c9566-37d2-4ab2-b891-89a203de4cdf · inbound

Relational Linear Properties in Language Models: An Empirical Investigation cites this paper.

Relational Linear Properties in Language Models: An Empirical Investigation Open Problems in Mechanistic Interpretability

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:46:15.014015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 43b05f4a-3053-40c4-92e1-e2c0fc207530 · inbound

Relational Linear Properties in Language Models: An Empirical Investigation cites this paper.

Relational Linear Properties in Language Models: An Empirical Investigation Open Problems in Mechanistic Interpretability

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:14:56.781346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f7a3be11-03e7-4581-8494-14c97ca3fb21 · inbound

Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing cites this paper.

Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing Open Problems in Mechanistic Interpretability

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-29T14:03:29.439485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9155af1c-7b97-4a31-a89d-d98f687d60f9 · inbound

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability cites this paper.

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability Open Problems in Mechanistic Interpretability

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-28T02:11:29.091386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 33e2b1c3-99b2-4f9c-a1f8-9cc668a95aaf · inbound

Necessary, Decodable and Reversible, Yet Not Transferable: A Stress Test for Attention-Head Role Claims cites this paper.

Necessary, Decodable and Reversible, Yet Not Transferable: A Stress Test for Attention-Head Role Claims Open Problems in Mechanistic Interpretability

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-02T21:47:27.708321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c4f2eab3-fea5-4e2f-845e-f7ef0c831a57 · inbound

From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs cites this paper.

From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs Open Problems in Mechanistic Interpretability

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-07-03T01:57:32.398548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 55d6c3bb-6377-4b1c-91a0-2aadc661fb90 · inbound

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal cites this paper.

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal Open Problems in Mechanistic Interpretability

Reference 87

Resolution: verified exact; local_arxiv, observed 2026-07-03T09:07:47.895988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a1c88b3d-f970-4ee2-a3c0-cf859e63efc9 · inbound

Learning Dynamics of Chain-of-Thought State Tracking in a Solvable Transformer Model cites this paper.

Learning Dynamics of Chain-of-Thought State Tracking in a Solvable Transformer Model Open Problems in Mechanistic Interpretability

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-03T23:39:05.249303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0aff0b28-aaa9-421b-8ed5-7d955597a588 · inbound

Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds cites this paper.

Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds Open Problems in Mechanistic Interpretability

Reference 116

Resolution: verified exact; local_arxiv, observed 2026-07-04T17:09:58.962774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 49197e46-f0cc-4439-ba2a-693b072f57a3 · inbound

Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders cites this paper.

Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders Open Problems in Mechanistic Interpretability

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-07-03T20:18:55.788579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e20f4c55-112c-4abd-9bca-ff9adfac4a08 · inbound

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources cites this paper.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Open Problems in Mechanistic Interpretability

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c5a2a1-ba7b-4c2b-a206-d130a5e166fe · inbound

Unsupervised Features Mining via Activation Geometry cites this paper.

Unsupervised Features Mining via Activation Geometry Open Problems in Mechanistic Interpretability

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T20:51:42.052454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 925f8d3b-88dd-4495-aa4a-3fe6e71c89fb · inbound

Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories cites this paper.

Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories Open Problems in Mechanistic Interpretability

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-09T19:46:28.683089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 14bd7dad-d5fd-480c-9cea-ef3020aba4bc · inbound

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning cites this paper.

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning Open Problems in Mechanistic Interpretability

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-09T15:06:18.032089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8255463b-7d81-4aa7-a958-0bdf24a853db · inbound

Laguerre Geometry for Interpreting Large Language Models cites this paper.

Laguerre Geometry for Interpreting Large Language Models Open Problems in Mechanistic Interpretability

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T10:42:30.055074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90bedcb2-6a35-442e-a894-69f72a24cca6 · inbound

Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.

Targeted Recovery of Weight-Space Mechanisms From Neural Networks Open Problems in Mechanistic Interpretability

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T10:39:48.676625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f612be05-850c-4c8f-bb3a-4aa956228a1b · inbound

Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.

Targeted Recovery of Weight-Space Mechanisms From Neural Networks Open Problems in Mechanistic Interpretability

Reference 175

Resolution: unresolved; no resolver link, observed 2026-08-02T10:40:03.484884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83e2ae79-c125-498c-9332-d3f102e15528 · inbound

Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods cites this paper.

Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods Open Problems in Mechanistic Interpretability

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T10:46:51.069511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c622027-b414-473d-abdf-cdeb1c968870 · inbound

Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control cites this paper.

Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control Open Problems in Mechanistic Interpretability

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T00:42:34.779473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6250a2e1-3dde-4b5d-ba0e-b62f793ffa87 · inbound

An Analysis of Residual-Stream Geometry Across Transformer Depth cites this paper.

An Analysis of Residual-Stream Geometry Across Transformer Depth Open Problems in Mechanistic Interpretability

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T17:18:44.974316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8675a0bb-2478-488f-99a4-f67be5a1fa3d · inbound

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models cites this paper.

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models Open Problems in Mechanistic Interpretability

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T12:14:23.380605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 865ee866-0a31-4a2e-a205-505620e1f5a6 · inbound

AGNFormer I: Reconstruction of AGN spectra using a probabilistic transformer model cites this paper.

AGNFormer I: Reconstruction of AGN spectra using a probabilistic transformer model Open Problems in Mechanistic Interpretability

Reference 125

Resolution: unresolved; no resolver link, observed 2026-08-01T12:16:42.768478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 084596d9-7682-4911-b82e-071205ac7e7b · inbound

Emergent Latent-State Computation under Stochastic Volatility cites this paper.

Emergent Latent-State Computation under Stochastic Volatility Open Problems in Mechanistic Interpretability

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T02:27:03.485740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcfd39c0-cf36-4cde-8840-92ba590592f8 · inbound

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs cites this paper.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Open Problems in Mechanistic Interpretability

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-31T23:07:40.684953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.