© 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. 51865
    Prev
    Next
    INDEX
    Explanations

    pass, 4, 0, or count as variables/arguments

    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
    ×ŀ×¢
    -0.08
    hower
    -0.07
    .setdefault
    -0.07
    ÙħÙİا
    -0.07
    rists
    -0.06
    innie
    -0.06
    à¸ļรม
    -0.06
     vén
    -0.06
    约车
    -0.06
    subscribe
    -0.06
    POSITIVE LOGITS
     tadi
    0.09
     stored
    0.08
     recalled
    0.08
    åŁİåįĹ
    0.08
    åı¬åĽŀ
    0.07
     previously
    0.07
    _REFRESH
    0.07
    Holder
    0.07
     accumulated
    0.07
    Stored
    0.07
    Activations Density 0.409%

    No Known Activations