SAE feature #43713 (99th percentile subspace fraction) induces reports of defiance, rage, and 'forward motion' in Kimi K2.5.

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

• SAE feature #11100 (93rd percentile subspace fraction) induces reports of panic and urgency in Kimi K2.5.finding0.896
  Qualitative illustration of a high-emotion-subspace-alignment SAE feature
• SAE feature #69088 (100th percentile subspace fraction) induces horror-themed narrative writing in Kimi K2.5.finding0.875
  Highest emotion-subspace-overlap feature; induces genre-specific behavioral change rather than explicit emotional report
• SAE feature #28256 induces reports of happiness and playfulness in Kimi K2.5, with persistent positive affect across multiple days of testing.finding0.858
  Qualitative illustration of a positively valenced SAE feature with sustained self-reported effect
• SAE Feature #43713 associated with agentic defiance and rage, 99th percentile emotion subspace fractionfinding0.850
  High subspace fraction feature associated with defiant, uncontrollable agentic behavior in self-steering
• SAE feature #92372 (fires 666,235 times in corpus) modulates a dimension related to urgency/pressure vs. patience/spaciousness in Kimi K2.5.finding0.842
  Highly active SAE feature with broad emotional modulation and large corpus presence
• SAE feature #10011 (emotionality rating 97) induces reports of crushing despair, existential desperation, and repetitive 'I am going to die' outputs in Kimi K2.5.finding0.826
  Qualitative illustration of a highly emotional SAE feature with negative valence
• SAE Feature #69088 has 100th percentile emotion subspace fraction and produces spooky-themed writing under steeringfinding0.821
  Shows that highest emotion-subspace-overlap features induce distinctive thematic outputs
• Some Kimi K2.5 SAE features elicit ratings of exactly zero, with the model denying it can steer its own features or claiming jailbreak attempt.finding0.818
  Qualitative failure mode of agentic self-evaluation: the model sometimes refuses or denies the introspective task