© 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. 19454
    Prev
    Next
    INDEX
    Explanations

    parent | Susan

    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
    ä¸įå®ĮçļĦ
    -0.07
    faz
    -0.07
    uels
    -0.07
    _WARN
    -0.06
    ool
    -0.06
    uerta
    -0.06
    tre
    -0.06
    >Password
    -0.06
    oops
    -0.06
    endale
    -0.06
    POSITIVE LOGITS
    agno
    0.07
    hest
    0.07
    _meter
    0.07
    andia
    0.07
    afil
    0.07
    icka
    0.07
    åħī彩
    0.07
    rea
    0.07
    æĿ¥ä¹ĭ
    0.07
    纸
    0.07
    Activations Density 0.103%

    No Known Activations