Paper Citation Record · LEDGER

Query Circuits: Explaining How Language Models Answer User Prompts

As of 8 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2509.24808.

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

pith.paper-citation-record.v1
2509.24808 v2

Coverage vector

measured 54 of 54 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T13:54:30.464863Z

measured 54 of 54 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

54 of 54 outbound references displayed

verified exact0
verified fuzzy0
unresolved53
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f4d4d839-6272-4587-a212-76821e6a22eb · outbound

This paper cites write newline.

Query Circuits: Explaining How Language Models Answer User Prompts write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:17.721691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79a915e4-0095-4b8b-80f3-7b45132bf767 · outbound

This paper cites Explainability for artificial intelligence in healthcare: a multidisciplinary perspective.

Query Circuits: Explaining How Language Models Answer User Prompts Explainability for artificial intelligence in healthcare: a multidisciplinary perspective

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:17.902861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e7e68a2-11f7-4059-8117-4234e91c3f35 · outbound

This paper cites Circuit tracing: Revealing computational graphs in language models.

Query Circuits: Explaining How Language Models Answer User Prompts Circuit tracing: Revealing computational graphs in language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:18.446117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f352892a-fd39-498a-8b45-e364f14f061b · outbound

This paper cites Claude 3.5 sonnet.

Query Circuits: Explaining How Language Models Answer User Prompts Claude 3.5 sonnet

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:18.668126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04c45940-a176-44d6-a3ab-989bc0cb15c7 · outbound

This paper cites Mechanistic interpretability for AI safety - a review.

Query Circuits: Explaining How Language Models Answer User Prompts Mechanistic interpretability for AI safety - a review

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:18.811332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2382c8b9-f57a-405b-92e7-d25e4f6755ae · outbound

This paper cites Building and evaluating alignment auditing agents.

Query Circuits: Explaining How Language Models Answer User Prompts Building and evaluating alignment auditing agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:18.931226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae9dfe80-c2ae-42a9-97ae-962424258fcb · outbound

This paper cites How people use chatgpt.

Query Circuits: Explaining How Language Models Answer User Prompts How people use chatgpt

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:19.068797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1d850d3-47ad-48f4-b2c6-5d2b92a2824b · outbound

This paper cites Selfie: self-interpretation of large language model embeddings.

Query Circuits: Explaining How Language Models Answer User Prompts Selfie: self-interpretation of large language model embeddings

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:19.205565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2d5e69d-65a0-4a74-ad3f-9a993e98964f · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Query Circuits: Explaining How Language Models Answer User Prompts Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:19.444737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a962c681-15dc-442b-9f2b-b58e0fa4f7cb · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability.

Query Circuits: Explaining How Language Models Answer User Prompts Towards automated circuit discovery for mechanistic interpretability

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:19.552979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 734ddd38-48ec-4d8e-b833-4b99e23159e1 · outbound

This paper cites The llama 3 herd of models.

Query Circuits: Explaining How Language Models Answer User Prompts The llama 3 herd of models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:19.615533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 212102ca-af1e-487d-8a3c-9e10e97a3216 · outbound

This paper cites A mathematical framework for transformer circuits.

Query Circuits: Explaining How Language Models Answer User Prompts A mathematical framework for transformer circuits

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:19.692097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0f01576-1489-4645-ba66-5a063e51d9fe · outbound

This paper cites N2g: A SCALABLE APPROACH FOR QUANTIFYING INTERPRETABLE NEURON REPRESENTATION IN LLMS.

Query Circuits: Explaining How Language Models Answer User Prompts N2g: A SCALABLE APPROACH FOR QUANTIFYING INTERPRETABLE NEURON REPRESENTATION IN LLMS

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:19.797259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5109528e-e556-4cfc-bb5b-a1e8bea33e74 · outbound

This paper cites The lottery ticket hypothesis: Finding sparse, trainable neural networks.

Query Circuits: Explaining How Language Models Answer User Prompts The lottery ticket hypothesis: Finding sparse, trainable neural networks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:19.879660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 029231fb-37f2-493e-a778-02f823316d25 · outbound

This paper cites Patchscopes: A unifying framework for inspecting hidden representations of language models.

Query Circuits: Explaining How Language Models Answer User Prompts Patchscopes: A unifying framework for inspecting hidden representations of language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:20.259029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70707aba-a473-4ea2-bb89-dda20dc8e339 · outbound

This paper cites How does GPT -2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model.

Query Circuits: Explaining How Language Models Answer User Prompts How does GPT -2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:20.454746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbb6ef4b-b766-4792-9a15-0ec4c2aeea68 · outbound

This paper cites Have faith in faithfulness: Going beyond circuit overlap when finding model mechanisms.

Query Circuits: Explaining How Language Models Answer User Prompts Have faith in faithfulness: Going beyond circuit overlap when finding model mechanisms

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:20.713859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c3d170-45c6-4798-9b63-d4cd2f086b7d · outbound

This paper cites Measuring massive multitask language understanding.

Query Circuits: Explaining How Language Models Answer User Prompts Measuring massive multitask language understanding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:21.214962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1133d2ac-0a7b-469a-8e54-6dd4cfaa6a72 · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Query Circuits: Explaining How Language Models Answer User Prompts Sparse autoencoders find highly interpretable features in language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:21.714748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb71268b-6f96-4dc3-8987-cd13e78e5771 · outbound

This paper cites GPT-4o System Card.

Query Circuits: Explaining How Language Models Answer User Prompts GPT-4o System Card

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:21.914743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e21beb9-6e37-49e0-82e8-4cc58c786beb · outbound

This paper cites Guided integrated gradients: An adaptive path method for removing noise.

Query Circuits: Explaining How Language Models Answer User Prompts Guided integrated gradients: An adaptive path method for removing noise

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:22.229386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05566e26-9d60-4170-9610-d5891fc0f97b · outbound

This paper cites Scaling sparse feature circuit finding for in-context learning.

Query Circuits: Explaining How Language Models Answer User Prompts Scaling sparse feature circuit finding for in-context learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:22.819735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3f2e374-e8f8-442d-bb18-1a9c22984bce · outbound

This paper cites Why are saliency maps noisy? cause of and solution to noisy saliency maps.

Query Circuits: Explaining How Language Models Answer User Prompts Why are saliency maps noisy? cause of and solution to noisy saliency maps

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:23.274745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f73ce20-d180-4d8b-8191-84152e1ff8af · outbound

This paper cites Granular concept circuits: Toward a fine-grained circuit discovery for concept representations.

Query Circuits: Explaining How Language Models Answer User Prompts Granular concept circuits: Toward a fine-grained circuit discovery for concept representations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:23.444738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97483b6c-6363-4de4-b00d-cc98d40802e6 · outbound

This paper cites Towards interpretable sequence continuation: Analyzing shared circuits in large language models.

Query Circuits: Explaining How Language Models Answer User Prompts Towards interpretable sequence continuation: Analyzing shared circuits in large language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:23.630175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a801a7-2116-4e0d-b55a-c55772cad573 · outbound

This paper cites Reddi, Ke Ye, Felix Chern, Felix Yu, Ruiqi Guo, and Sanjiv Kumar.

Query Circuits: Explaining How Language Models Answer User Prompts Reddi, Ke Ye, Felix Chern, Felix Yu, Ruiqi Guo, and Sanjiv Kumar

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:23.834745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3f8437e-b39d-4465-b3c2-b446672c0bad · outbound

This paper cites an unresolved cited work.

Query Circuits: Explaining How Language Models Answer User Prompts Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:24.304745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30ed61c6-7e98-4eff-9fe6-9eb58c54c8fc · outbound

This paper cites Sparse crosscoders for cross-layer features and model diffing.

Query Circuits: Explaining How Language Models Answer User Prompts Sparse crosscoders for cross-layer features and model diffing

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:24.694742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c416d55d-9250-4fbd-8b81-3e9fd141cdcc · outbound

This paper cites Lundberg and Su-In Lee.

Query Circuits: Explaining How Language Models Answer User Prompts Lundberg and Su-In Lee

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:24.892022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 588a5a40-fcbb-44db-97e7-6ee30c0ec064 · outbound

This paper cites Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders.

Query Circuits: Explaining How Language Models Answer User Prompts Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:25.164744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2de75ddd-d452-4f1a-9219-90f138154d0d · outbound

This paper cites Sparse feature circuits: Discovering and editing interpretable causal graphs in language models.

Query Circuits: Explaining How Language Models Answer User Prompts Sparse feature circuits: Discovering and editing interpretable causal graphs in language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:25.524740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d10b0ac-e141-4765-918a-d5130f039198 · outbound

This paper cites Transformer circuit evaluation metrics are not robust.

Query Circuits: Explaining How Language Models Answer User Prompts Transformer circuit evaluation metrics are not robust

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:25.718628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 933f0a15-6036-4547-9c0a-8ed70f903cfa · outbound

This paper cites MIB : A mechanistic interpretability benchmark.

Query Circuits: Explaining How Language Models Answer User Prompts MIB : A mechanistic interpretability benchmark

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:25.834746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5350bdad-f499-48bf-8345-ef6805f21605 · outbound

This paper cites Transformerlens.

Query Circuits: Explaining How Language Models Answer User Prompts Transformerlens

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:25.939819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45efce2f-4452-4411-990c-9b7f6648d357 · outbound

This paper cites A toy model of mechanistic (un)faithfulness.

Query Circuits: Explaining How Language Models Answer User Prompts A toy model of mechanistic (un)faithfulness

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:26.084741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17e702b3-8f86-40ab-82c1-01b8ed397f78 · outbound

This paper cites Explanations in autonomous driving: A survey.

Query Circuits: Explaining How Language Models Answer User Prompts Explanations in autonomous driving: A survey

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:26.294736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 487767cb-4588-47d7-a3a5-96094e7962f3 · outbound

This paper cites Understanding addition in transformers.

Query Circuits: Explaining How Language Models Answer User Prompts Understanding addition in transformers

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:26.465383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1720b02c-9d6b-4550-955b-20e497f08752 · outbound

This paper cites Language models are unsupervised multitask learners.

Query Circuits: Explaining How Language Models Answer User Prompts Language models are unsupervised multitask learners

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:26.818340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d620e14-f234-490e-9d2d-e7cb44c9be74 · outbound

This paper cites A multimodal automated interpretability agent.

Query Circuits: Explaining How Language Models Answer User Prompts A multimodal automated interpretability agent

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:27.000653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c86b015-dbff-4b1c-8127-6e11c328f34f · outbound

This paper cites A value for n-person games.

Query Circuits: Explaining How Language Models Answer User Prompts A value for n-person games

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:27.154822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54031f87-3184-4e11-8f72-2eb92d2e75e3 · outbound

This paper cites SmoothGrad: removing noise by adding noise.

Query Circuits: Explaining How Language Models Answer User Prompts SmoothGrad: removing noise by adding noise

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:27.304731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4693b4e5-cf4e-4eda-acce-e135201a7363 · outbound

This paper cites Axiomatic attribution for deep networks.

Query Circuits: Explaining How Language Models Answer User Prompts Axiomatic attribution for deep networks

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:27.834819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ba73055-919d-461a-9921-e115c2357340 · outbound

This paper cites Attribution patching outperforms automated circuit discovery.

Query Circuits: Explaining How Language Models Answer User Prompts Attribution patching outperforms automated circuit discovery

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:28.144739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cd0ff9c-bed0-48e6-af08-769458b88b8b · outbound

This paper cites Universal properties of activation sparsity in modern large language models.

Query Circuits: Explaining How Language Models Answer User Prompts Universal properties of activation sparsity in modern large language models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:28.454741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 627eb20d-080c-45ad-90de-ab701a6c96e4 · outbound

This paper cites Daniel Freeman, Theodore R.

Query Circuits: Explaining How Language Models Answer User Prompts Daniel Freeman, Theodore R

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:28.624743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 615a725f-6b9d-40c1-9a6c-28caabc9835a · outbound

This paper cites Investigating gender bias in language models using causal mediation analysis.

Query Circuits: Explaining How Language Models Answer User Prompts Investigating gender bias in language models using causal mediation analysis

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:28.735017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4e1f734-d0bb-4a0d-a48f-b5ccf8da2a98 · outbound

This paper cites Interpretability in the wild: a circuit for indirect object identification in GPT -2 small.

Query Circuits: Explaining How Language Models Answer User Prompts Interpretability in the wild: a circuit for indirect object identification in GPT -2 small

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:28.954740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d43e82cf-b025-441d-bf40-f6904e5edaef · outbound

This paper cites Do LLM s overcome shortcut learning? an evaluation of shortcut challenges in large language models.

Query Circuits: Explaining How Language Models Answer User Prompts Do LLM s overcome shortcut learning? an evaluation of shortcut challenges in large language models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:29.116406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83748693-4fae-4d0e-ba4e-3534a98052bf · outbound

This paper cites Towards best practices of activation patching in language models: Metrics and methods.

Query Circuits: Explaining How Language Models Answer User Prompts Towards best practices of activation patching in language models: Metrics and methods

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:29.284826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3c46278-2027-4a37-9d16-ccf65a3ffe56 · outbound

This paper cites EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification.

Query Circuits: Explaining How Language Models Answer User Prompts EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:29.774749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd0d2b73-2332-4bfe-a8a1-17d71037c653 · outbound

This paper cites Large language models are not robust multiple choice selectors.

Query Circuits: Explaining How Language Models Answer User Prompts Large language models are not robust multiple choice selectors

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:29.907920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aee4008-8888-4965-bb36-84c2ae6e05f4 · outbound

This paper cites @esa (Ref.

Query Circuits: Explaining How Language Models Answer User Prompts @esa (Ref

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:30.254747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0daa7992-1641-4828-9198-d9111ae502de · outbound

This paper cites an unresolved cited work.

Query Circuits: Explaining How Language Models Answer User Prompts Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T13:54:30.344819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32f82c2f-ab88-4407-bc38-3cb9444e6596 · outbound

This paper cites How to use and interpret activation patching.

Query Circuits: Explaining How Language Models Answer User Prompts How to use and interpret activation patching

Reference 55

Resolution: malformed identifier; no resolver link, observed 2026-08-04T13:54:30.464863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.