© 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. 37951
    Prev
    Next
    INDEX
    Explanations

    maven artifact id

    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
    onnier
    -0.08
    ÑģÑĤвоÑĤо
    -0.07
    .biz
    -0.07
    uiltin
    -0.07
    ouve
    -0.07
    onha
    -0.07
    scal
    -0.07
    STA
    -0.07
    æ¡ĥæĿİ
    -0.07
     übern
    -0.07
    POSITIVE LOGITS
    zÄĻ
    0.07
    latest
    0.07
     latest
    0.07
    integ
    0.07
    ä¸įåĪĨ
    0.07
    _PATCH
    0.06
    æľĢæĸ°çīĪ
    0.06
     Estatal
    0.06
    æŁĶç¾İ
    0.06
    æľĢæĸ°
    0.06
    Activations Density 0.041%

    No Known Activations