© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44155
    Prev
    Next
    INDEX
    Explanations

    heroes and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    伯ä¹IJ
    -0.08
    模æĭŁ
    -0.07
    奴
    -0.07
    欣
    -0.06
    å®ī详
    -0.06
    éĺ
    -0.06
     Madness
    -0.06
    æĹ¥çĶ¨
    -0.06
    éŃĶ鬼
    -0.06
    大象
    -0.06
    POSITIVE LOGITS
    ulti
    0.08
    æĬ¤éĢģ
    0.08
    æķijåĩº
    0.08
     missions
    0.08
    并èĤ©
    0.08
    ç»ĦéĺŁ
    0.08
    ä¿ĿèŃ·
    0.08
    uwe
    0.08
     protect
    0.08
    ä¿ĿæĬ¤å¥½
    0.08
    Activations Density 0.244%

    No Known Activations