© 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. 32270
    Prev
    Next
    INDEX
    Explanations

    purpose, objective, context, synopsis

    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¸įè¿ĩè¿Ļ
    -0.06
    Ñħий
    -0.06
    mand
    -0.06
    endo
    -0.06
     ná»ķi
    -0.06
    AccessType
    -0.06
    is
    -0.06
    å¥ĭ
    -0.06
    Ñħов
    -0.06
    éĶIJæĦıè¿Ľåıĸ
    -0.06
    POSITIVE LOGITS
    .fin
    0.08
    æ¦Ī
    0.08
    adu
    0.08
    reau
    0.07
    gül
    0.07
    adoo
    0.07
    adesh
    0.07
     tre
    0.07
    pread
    0.07
    igl
    0.07
    Activations Density 0.085%

    No Known Activations