Paper Citation Record · LEDGER

Learning Multi-Level Features with Matryoshka Sparse Autoencoders

As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 43 inbound Pith citation observations for arXiv:2503.17547.

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

pith.paper-citation-record.v1
2503.17547 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 43 of 43 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:46:16.512841Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 10b64f59-8fbe-4986-b96d-8f7e92bc671d · inbound

BlueGlass: A Framework for Composite AI Safety cites this paper.

BlueGlass: A Framework for Composite AI Safety Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:16.512841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae2e7e69-ddb3-45ce-9d79-37508d945371 · inbound

Insights into a radiology-specialised multimodal large language model with sparse autoencoders cites this paper.

Insights into a radiology-specialised multimodal large language model with sparse autoencoders Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T16:40:41.151327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd93be14-1c3c-4914-b46a-4a3b389dff4b · inbound

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders cites this paper.

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-05T17:18:54.254819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a58229d-fb4e-4aa8-8b74-8d83bd295050 · 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 Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T18:47:45.260976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c4f7495-47a9-48a4-a50d-a1c8e379146f · inbound

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework cites this paper.

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-18T18:16:43.795195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7a8ad517-1171-4701-8618-4be505441825 · inbound

Towards Atoms of Large Language Models cites this paper.

Towards Atoms of Large Language Models Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.122570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0349ddfd-a514-451c-9bfa-85a6ee2afee6 · inbound

Mechanistic Interpretability of Antibody Language Models Using SAEs cites this paper.

Mechanistic Interpretability of Antibody Language Models Using SAEs Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T18:21:10.192574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a389fd-ec55-4b82-bf1f-d86919984c36 · inbound

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding cites this paper.

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T05:48:08.046788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ade5bafd-71bb-4827-a4e3-777439b4889c · inbound

Stable and Steerable Sparse Autoencoders with Weight Regularization cites this paper.

Stable and Steerable Sparse Autoencoders with Weight Regularization Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T18:56:20.402722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b3f94b-a4ce-461d-ae04-256f59d7ed20 · inbound

Improving Robustness In Sparse Autoencoders via Masked Regularization cites this paper.

Improving Robustness In Sparse Autoencoders via Masked Regularization Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T23:55:51.694717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7d293bf9-e144-4fcf-9ca0-d8fdde9a88ca · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:35:57.369684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba62daa4-e5e8-4f4c-9eef-566affe5ee70 · inbound

From Tokens to Concepts: Leveraging SAE for SPLADE cites this paper.

From Tokens to Concepts: Leveraging SAE for SPLADE Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:11:07.816562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e57f8934-c8c5-4bd3-876e-c60283122d21 · inbound

From Tokens to Concepts: Leveraging SAE for SPLADE cites this paper.

From Tokens to Concepts: Leveraging SAE for SPLADE Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-04T23:30:12.038645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9a842034-6079-415b-b9c7-dd8349be1e47 · inbound

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cites this paper.

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:15:54.324345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2ef61865-a337-4a47-8efc-dd15032e932a · inbound

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cites this paper.

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:16:25.309504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c308cd1a-c6c9-4d08-8174-c8c08ee1d91a · inbound

Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions cites this paper.

Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:16:30.283057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4535f8b1-44e4-43b3-be19-a86ad1d49825 · inbound

Do Language Models Encode Knowledge of Linguistic Constraint Violations? cites this paper.

Do Language Models Encode Knowledge of Linguistic Constraint Violations? Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:27:24.757936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 85f509fb-4327-4872-b295-db4d6f68327a · inbound

Do Language Models Encode Knowledge of Linguistic Constraint Violations? cites this paper.

Do Language Models Encode Knowledge of Linguistic Constraint Violations? Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:45:05.715255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4212971a-d40a-4f76-add1-5c3847628cf5 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 59

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:59:28.815697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 050f8176-bb23-4cb4-9104-f83203f5186e · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 59

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T04:59:45.210865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5d789e60-1136-4590-985d-75bb3bca272d · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 59

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T21:53:47.204449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 538895f4-9bdb-4016-bc9d-a3bd480da609 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:49:50.149450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 73bbb688-d283-4122-9be1-700e48d61927 · inbound

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features cites this paper.

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:27:58.925563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d94daa48-28f1-402c-bbaa-fe58c648ac45 · inbound

The Rate-Distortion-Polysemanticity Tradeoff in SAEs cites this paper.

The Rate-Distortion-Polysemanticity Tradeoff in SAEs Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T21:15:04.074818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ef29cbe4-5fbc-4e64-8cdd-37a10931f375 · inbound

Are Sparse Autoencoder Benchmarks Reliable? cites this paper.

Are Sparse Autoencoder Benchmarks Reliable? Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T12:43:16.816953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f9ab20dc-5b04-44e6-96d4-3a87316872b0 · inbound

Probing for Representation Manifolds in Superposition cites this paper.

Probing for Representation Manifolds in Superposition Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 43

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T11:48:15.054342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1aa28f09-e98d-4638-8563-a6a8a45b07d2 · inbound

Matryoshka Concept Bottleneck Models cites this paper.

Matryoshka Concept Bottleneck Models Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T18:04:57.912098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 20488253-1250-4e39-92ef-a6aa019f498b · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T14:23:30.768006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation afbcad70-c0ed-4f22-9375-fbd162d4110c · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T05:02:51.359419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc41b531-7c3f-463f-8791-120635d82074 · inbound

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

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T02:11:29.051237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 85168b2f-b7ad-4caa-97bf-d31e57e4f8f9 · inbound

MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework cites this paper.

MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-02T07:26:45.679414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aeadf5f0-deac-45d1-9fed-5caa5f84796c · inbound

VFUSE: Virulent Feature Understanding with Sparse autoEncoders cites this paper.

VFUSE: Virulent Feature Understanding with Sparse autoEncoders Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:57:29.990683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aeb88284-f81f-4280-b1ef-a3b12b0169bb · inbound

ICA Lens: Interpreting Language Models Without Training Another Dictionary cites this paper.

ICA Lens: Interpreting Language Models Without Training Another Dictionary Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T09:17:49.077422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ff56213b-bead-4e9a-9612-d63740a43f46 · 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 Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 245

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T09:07:47.947301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 74f60525-2cdd-419e-8585-cb92693ab7d4 · inbound

Rational Sparse Autoencoder cites this paper.

Rational Sparse Autoencoder Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:08:43.960948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b41c211-49cd-45e5-9a40-b0e7ed98e96a · inbound

Critical Percolation as a Synthetic Data Model for Interpretability cites this paper.

Critical Percolation as a Synthetic Data Model for Interpretability Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T03:49:29.645376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bc2e77cb-2669-4fcd-9876-9963fac35238 · inbound

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies? cites this paper.

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies? Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T10:29:45.362219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation abe129d7-1364-4adf-a138-539e04a2db16 · inbound

Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders cites this paper.

Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:39:50.936158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 347c5b27-8d15-4393-b4b0-5a027fbf95d6 · inbound

Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders cites this paper.

Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-15T10:30:51.183063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5910d1d-1615-4ca3-83de-1c75d4d5eebd · inbound

Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution cites this paper.

Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-01T15:35:48.366795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ac712014-e362-469d-b601-5d72cfb819f4 · inbound

Monosemanticity in Recommender Systems cites this paper.

Monosemanticity in Recommender Systems Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T02:34:13.627523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 96fc9cef-3493-4c34-882d-f0b5b9ba7a35 · inbound

Monosemanticity in Recommender Systems cites this paper.

Monosemanticity in Recommender Systems Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T22:49:00.652630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b17ebd3c-35dd-4b26-a41c-b9f4ace6dd43 · inbound

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability cites this paper.

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:28:44.170293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.