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.

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

• Self-evaluated emotionality and textual evaluation of SAE features predict persistence in opposite directions.claim0.881
  Surprising finding that the two evaluation methods diverge in their relationship with persistence
• Agentic self-evaluation of SAE feature emotionality correlates with residual persistence: ρ = +0.124, p = 0.0001 in Kimi K2.5.finding0.877
  Shows that model self-report of emotion predicts long-range feature persistence
• Agentic self-evaluation emotionality correlates with SAE feature persistence: rho=+0.124, p=0.0001finding0.868
  Shows that features Kimi rates as more emotional via self-steering are more persistent, independent of probe construction
• Text-based and self-steered emotionality ratings for SAE features are correlated at only ρ = +0.051 (n.s.).finding0.867
  Shows low agreement between the two evaluation modalities
• Correlation between self-evaluation and textual evaluation of SAE feature emotionality: rho=+0.051 (n.s.)finding0.844
  Shows that the two evaluation methods for emotionality are largely uncorrelated, indicating they capture different signals
• Textual evaluation emotionality weakly negatively correlates with SAE feature persistencefinding0.840
  Contrasts with positive correlation from agentic self-evaluation, suggesting text and self-evaluation capture different aspects
• 17 of 83 emotions tested show significant associations between SAE feature self-evaluation transcripts mentioning the emotion word and higher cosine similarity to that emotion probe; 67 of 83 have positive associations.finding0.840
  Demonstrates partial but reliable validity of self-evaluation for measuring probe emotionality
• 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.)claim0.835
  Interprets the near-zero correlation between the two evaluation methods as evidence they capture distinct signals