35 citations · 81 across the 27 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CL2026
A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals
Yuri Son, Seunghee Kim, Hyuhng Joon Kim +1
Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate safety policies (safety-based re…
cs.LG2026
Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
Hwiyeong Lee, Ingyu Bang, Uiji Hwang +2
While sparse autoencoders provide features more interpretable than individual neurons, reliably characterizing them remains challenging. We propose Query Lens, which extends Logit…