© 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. 42016
    Prev
    Next
    INDEX
    Explanations

    % volatility and entropy

    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
    antie
    -0.09
    immat
    -0.08
    hdl
    -0.08
    å¼Ĥ常
    -0.08
     harmless
    -0.07
     miniature
    -0.07
    metatable
    -0.07
    arki
    -0.07
    umed
    -0.07
     eroti
    -0.07
    POSITIVE LOGITS
     decom
    0.07
    elaar
    0.07
    leistungs
    0.07
    åĬŁ
    0.07
    ä¸įç®Ģåįķ
    0.07
    ear
    0.07
    æĭĨ
    0.07
    åĬłåĩı
    0.06
    vus
    0.06
     ÏĥÏħνα
    0.06
    Activations Density 0.026%

    No Known Activations