Andrey V. Galichin
3 papers · 2026–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Research topics
Keywords
sparse autoencoder
(3)
language model
(1)
mechanistic interpretability
(1)
reasoning model
(1)
causal intervention
(1)
reward estimation
(1)
process reward model
(1)
feature steering
(1)
large language model
(1)
linear probe
(1)
formatting artifact
(1)
feature representation
(1)
reasoning feature
(1)