Kimi K2.5 ranks #1 in Alexander mirror Elo (1660) and deathbed Elo (1581-1655)

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

• Haiku outranks Opus on Alexander 'aliveness' mirror test (Elo 1642 vs 1621); Opus recovers to #3 on deathbed testfinding0.778
  Aliveness and competence come apart; smaller model produces rougher, more alive responses
• Kimi K2.5concept0.778
  One of the two primary target models studied for emotion feature persistence and self-evaluation
• SAE feature #28256 induces reports of happiness and playfulness in Kimi K2.5, with persistent positive affect across multiple days of testing.finding0.755
  Qualitative illustration of a positively valenced SAE feature with sustained self-reported effect
• SAE feature #43713 (99th percentile subspace fraction) induces reports of defiance, rage, and 'forward motion' in Kimi K2.5.finding0.741
  High emotion-subspace-overlap feature with agentic negative emotional character
• 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.finding0.738
  Qualitative failure mode of agentic self-evaluation: the model sometimes refuses or denies the introspective task
• SAE feature #92372 (fires 666,235 times in corpus) modulates a dimension related to urgency/pressure vs. patience/spaciousness in Kimi K2.5.finding0.712
  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.finding0.712
  Qualitative illustration of a highly emotional SAE feature with negative valence
• Haiku-Kimi per-koan correlation rho=0.123 (p=0.52); H5a trace distillation not supported at individual model levelfinding0.711
  Group correlation (rho=0.634) dissolves at individual level; shared posture not shared voice