© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58579
    Prev
    Next
    INDEX
    Explanations

    math symbols and notation

    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
    éĽªçIJĥ
    -0.07
    หลวà¸ĩ
    -0.07
    kker
    -0.07
    idend
    -0.07
    åİĭåĬĽå¤§
    -0.06
     dod
    -0.06
    éĺ³åħīæĺİåªļ
    -0.06
    ç³»ç»Łè®¾è®¡
    -0.06
    åIJĮ声
    -0.06
    åĩłæŃ¥
    -0.06
    POSITIVE LOGITS
     Ferrara
    0.08
    _between
    0.08
    .between
    0.07
    èŀ
    0.07
    ë¥
    0.07
     coils
    0.07
    天éŃĶ
    0.07
    UpDown
    0.07
    è½®
    0.07
    erras
    0.07
    Activations Density 0.002%

    No Known Activations