© 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. 25424
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    ç¼Ī
    -0.08
    ivet
    -0.08
    æľ¬ç«ĻåĨħ容
    -0.08
    toff
    -0.08
    жев
    -0.08
    eviÄĩ
    -0.07
    yum
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    ulat
    -0.07
     pens
    -0.07
    POSITIVE LOGITS
    esp
    0.07
    ä¸ĭ称
    0.07
    usser
    0.06
    0.06
     esp
    0.06
    /loader
    0.06
    æĻºèĢħ
    0.06
    åĩ
    0.06
    å¿«
    0.06
    ç©´
    0.06
    Activations Density 0.075%

    No Known Activations