© 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. 3801
    Prev
    Next
    INDEX
    Explanations

    module, year, MC, prom

    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
     ‘’
    -0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.08
    undi
    -0.08
     **,
    -0.08
     напо
    -0.07
    erti
    -0.07
    _notify
    -0.07
    uban
    -0.07
    κÏģα
    -0.07
    ropp
    -0.07
    POSITIVE LOGITS
    ____
    0.10
     ___
    0.10
     ____
    0.09
    ＿＿
    0.09
     \"
    0.08
     _____
    0.08
    (___
    0.08
     ______
    0.08
    <u
    0.08
    ___
    0.07
    Activations Density 0.275%

    No Known Activations