© 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. 40093
    Prev
    Next
    INDEX
    Explanations

    Higgs bosons, susy, scalar top, b -> cl, brachytherapy

    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
    urve
    -0.07
     io
    -0.06
     Eug
    -0.06
    累计
    -0.06
    汶
    -0.06
    .Android
    -0.06
    æ³ĵ
    -0.06
    ble
    -0.06
     thirsty
    -0.06
    ç´¯
    -0.06
    POSITIVE LOGITS
    ä¼ļåIJĮ
    0.08
    schau
    0.08
    æĿİå¿Ĺ
    0.08
    hares
    0.08
    _unused
    0.08
    epen
    0.08
    sync
    0.08
    öh
    0.08
    ÏĦία
    0.07
    _ptrs
    0.07
    Activations Density 0.003%

    No Known Activations