© 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. 37741
    Prev
    Next
    INDEX
    Explanations

    . and punctuation

    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
    pat
    -0.07
    pie
    -0.07
    éķ¿å¤Ħ
    -0.07
     nevertheless
    -0.07
    afx
    -0.06
    ein
    -0.06
    Ñİ
    -0.06
    Dispatcher
    -0.06
    ĵĺ
    -0.06
    eer
    -0.06
    POSITIVE LOGITS
    æīĢ以è¦ģ
    0.09
    èĭ¥è¦ģ
    0.09
    为äºĨ满足
    0.09
    éĻ¤éĿŀ
    0.09
    墨
    0.08
     unless
    0.08
    æķħ
    0.08
    è¦ģæĿ¥
    0.08
    èĭ¥æĥ³
    0.08
    ä¸įèĥ½æ»¡è¶³
    0.08
    Activations Density 0.010%

    No Known Activations