© 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. 38186
    Prev
    Next
    INDEX
    Explanations

    award recipients

    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
    alia
    -0.08
    erre
    -0.07
    меÑģÑĤ
    -0.07
    éĻĦ带
    -0.07
     Overse
    -0.07
    azan
    -0.07
    ç»ļ
    -0.06
    iao
    -0.06
    zzle
    -0.06
    atter
    -0.06
    POSITIVE LOGITS
    بات
    0.08
    ë°į
    0.07
    hausen
    0.07
    就好åĥı
    0.07
    å½·
    0.07
    è§Ĵ度æĿ¥çľĭ
    0.07
    å·´å·´
    0.07
    _utils
    0.07
    EMA
    0.07
    declspec
    0.07
    Activations Density 0.002%

    No Known Activations