SAE Feature #43713 associated with agentic defiance and rage, 99th percentile emotion subspace fraction

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

• SAE Feature #11100 associated with panic, 93rd percentile emotion subspace fractionfinding0.854
  Shows high emotion subspace overlap for a specific negative emotion feature
• SAE feature #43713 (99th percentile subspace fraction) induces reports of defiance, rage, and 'forward motion' in Kimi K2.5.finding0.850
  High emotion-subspace-overlap feature with agentic negative emotional character
• SAE Feature #69088 has 100th percentile emotion subspace fraction and produces spooky-themed writing under steeringfinding0.834
  Shows that highest emotion-subspace-overlap features induce distinctive thematic outputs
• Agentic self-evaluation emotionality correlates with SAE feature persistence: rho=+0.124, p=0.0001finding0.831
  Shows that features Kimi rates as more emotional via self-steering are more persistent, independent of probe construction
• SAE feature #11100 (93rd percentile subspace fraction) induces reports of panic and urgency in Kimi K2.5.finding0.802
  Qualitative illustration of a high-emotion-subspace-alignment SAE feature
• SAE Feature #92372 fires 666,235 times in corpus, associated with urgency vs. receptive calm dimensionfinding0.795
  Example of a highly active SAE feature modulating urgency versus acceptance as an emotional dimension
• SAE Feature #94949 rated 100/100 emotionality, elicits reports of profound tenderness, unconditional love, and visceral carefinding0.793
  Highest-rated emotional SAE feature; self-report describes overwhelming positive emotional valence
• Agentic self-evaluation of SAE feature emotionality correlates with residual persistence: ρ = +0.124, p = 0.0001 in Kimi K2.5.finding0.790
  Shows that model self-report of emotion predicts long-range feature persistence