© 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. 44163
    Prev
    Next
    INDEX
    Explanations

    cited hereinabove

    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
    _masks
    -0.07
    PUTE
    -0.07
    ç»ıæµİ
    -0.06
    <|box_end|>
    -0.06
    å¨ģ
    -0.06
    jel
    -0.06
    combe
    -0.06
    /footer
    -0.06
    isters
    -0.06
    iode
    -0.06
    POSITIVE LOGITS
     Patrimonio
    0.07
    åī¯åİ¿éķ¿
    0.07
     aforementioned
    0.07
    mentioned
    0.07
     mentioned
    0.07
    wend
    0.07
    é£İä¸Ń
    0.07
    EMAT
    0.07
    schul
    0.07
    áŁĭ
    0.07
    Activations Density 0.056%

    No Known Activations