Self-evaluated emotionality and textual evaluation of SAE features predict persistence in opposite directions.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Textual evaluation emotionality weakly negatively correlates with SAE feature persistencefinding0.893
  Contrasts with positive correlation from agentic self-evaluation, suggesting text and self-evaluation capture different aspects
• Self-evaluated emotionality of SAE features negatively correlates with activation variance explained (ρ = -0.184, p = 4.6e-09), requiring variance correction to reveal the persistence signal.finding0.881
  Explains why variance correction is needed to see the self-evaluation–persistence relationship
• SAE features that the model self-describes as more emotional tend to be more persistent than variance-matched SAE features.claim0.878
  Novel finding that agentic self-evaluation of emotionality correlates with feature persistence
• Textual evaluation and agentic self-evaluation of SAE feature emotionality measure different aspects of emotional content and correlate only weakly (rho=+0.051, n.s.)claim0.876
  Interprets the near-zero correlation between the two evaluation methods as evidence they capture distinct signals
• Agentic self-evaluation emotionality correlates with SAE feature persistence: rho=+0.124, p=0.0001finding0.859
  Shows that features Kimi rates as more emotional via self-steering are more persistent, independent of probe construction
• Agentic self-evaluation of SAE feature emotionality correlates with residual persistence: ρ = +0.124, p = 0.0001 in Kimi K2.5.finding0.859
  Shows that model self-report of emotion predicts long-range feature persistence
• Correlation between self-evaluation and textual evaluation of SAE feature emotionality: rho=+0.051 (n.s.)finding0.856
  Shows that the two evaluation methods for emotionality are largely uncorrelated, indicating they capture different signals
• Agentic self-steering evaluation may serve as a general method for explaining and interpreting SAE features beyond emotionclaim0.849
  Forward-looking claim about the broader utility of the self-steering evaluation method