Paper Citation Record · LEDGER

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head

As of 16 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 5 inbound Pith citation observations for arXiv:2501.02688.

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

pith.paper-citation-record.v1
2501.02688 v2

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T22:12:10.025780Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:44:55.391452Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T01:19:20.256751Z

Reference resolution

16 of 16 outbound references displayed

verified exact0
verified fuzzy0
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4e9e792a-ad1d-4660-a13e-a29623f32e8a · outbound

This paper cites an unresolved cited work.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:12:11.496121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ac64d724-5ca1-4070-89cd-e1e1c69d7757 · outbound

This paper cites Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-08-10T22:12:11.028983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 10bd4e7e-dae1-4bf2-99b9-b17c9045e8b3 · outbound

This paper cites The Llama 3 Herd of Models.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head The Llama 3 Herd of Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:09.654862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d065306b-be2f-46c8-9022-8d41e4db26b1 · outbound

This paper cites an unresolved cited work.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:12:11.462007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6d04ac8d-bc34-417d-b0cc-f4d4ba53578a · outbound

This paper cites Toy Models of Superposition.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Toy Models of Superposition

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:09.746929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5d70652-fa2d-4598-aa7a-68b4a440e8d9 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Scaling and evaluating sparse autoencoders

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:09.788924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a2186de-82a7-4bd0-af6d-2cd0cf24cbdd · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:09.831365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cabddd5-0413-437f-b423-aa1b2b3d9ec0 · outbound

This paper cites GPT-4 Technical Report.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head GPT-4 Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:09.847345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f5b370-77c3-417f-a981-8978a41b9f26 · outbound

This paper cites an unresolved cited work.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:12:11.424946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2c1cecc1-0282-4272-ad15-1c86d170cbc4 · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:09.884832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb818aa1-d80b-4103-bddd-383b57f3674a · outbound

This paper cites an unresolved cited work.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:09.921257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d77935c-ad94-470d-8bb4-2eea9de7c24f · outbound

This paper cites an unresolved cited work.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:12:11.384861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2546b259-dc4d-462c-8391-60d2002578e0 · outbound

This paper cites an unresolved cited work.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:12:11.264757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 87458d74-4ffe-4ca4-b123-542783770ed5 · outbound

This paper cites an unresolved cited work.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-10T22:12:11.159854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0bf5226d-0fa2-4c29-b25d-0dec5170fca6 · outbound

This paper cites online" 'onlinestring :=.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head online" 'onlinestring :=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:10.005901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7d273f4-7867-4ff9-b108-0641fae73964 · outbound

This paper cites write newline.

Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head write newline

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T22:12:10.025780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 3e387ea4-eb72-4cc5-9931-40d0cff0ecb5 · inbound

Steering Conceptual Bias via Transformer Latent-Subspace Activation cites this paper.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.391452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57e30a1d-a643-4a57-b8a0-52b6cff2489d · inbound

Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning cites this paper.

Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-21T16:25:21.198098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b6f8cda5-fdcf-4cc3-9556-4f88715baca9 · inbound

Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning cites this paper.

Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T13:11:01.018894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd5c7d5d-2aeb-45f2-9b88-cc2b911b1cf6 · inbound

Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction cites this paper.

Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:38:19.147959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 069dbc34-8fae-47de-b006-b9930c221f7f · inbound

Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction cites this paper.

Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-07-04T01:19:20.260285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.