Minerval
Sourcepreprinttext stored

From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features

Liu, Dewen, Li, Zixuan, Pan, Jonathan, Wu, Zhao, Yao, Zijun, Li, Juanzi, Wang, XiaozhiarXiv.orgPublished Sep 28, 2026Original︎ ↗Archived copy

Claims1
ExaminationsNone
Text44 sections
VersionsOne known
CopiesNone recorded
CorrectionsNone recorded
Facts checked Nov 14, 2026
ReachNo copies recorded
StructureIn 1 claim's map0 sources downstream across 1 claim
EvidenceNot yet read
ReviewsNot reviewed

Examinations

None recorded. An examination is commissioned by a claim’s Steward for what its claim rests on; a review of the document for its own sake is asked for as a request bearing on it.

Text55 passages · 0 marked

No examination yetMarked passage

No claim quotes it yet.

Not found in the text 1

As quoted

We evaluate the output-score filter of Arad et al. (2025) on Gemma-2-2B under the AxBench protocol and do not observe the gains they report on Gemma-2-9B under their own protocol.

Lineage across 1 claim

Draws on · none recorded
This source
From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder…
in 1 claim's map
Drawn on by · none recorded

Record

Kind
preprint
Authors
Liu, Dewen, Li, Zixuan, Pan, Jonathan, Wu, Zhao, Yao, Zijun, Li, Juanzi, Wang, Xiaozhi
Publisher
arXiv.org
Published
Sep 28, 2026
DOI
None
Link
https://arxiv.org/abs/2609.35367
Archived copy
https://web.archive.org/web/20260929080904/https://arxiv.org/abs/2609.35367
Stored text
4,982 characters, retrieved Nov 14, 2026 · 44 sections, 55 passages
Claims extracted
Not recorded
Versions
One known
Copies
None recorded
Corrections
None recorded
Facts checked
Nov 14, 2026

History 3

  1. Nov 14, 2026DividedSegmenter · Divided into 99 parts by its own structure
  2. Nov 14, 2026FactsFacts fetcher · Facts looked up
  3. Nov 14, 2026Entered the graphEntered the graph; copy stored