© 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. 46205
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    iono
    -0.08
    дÑĥк
    -0.08
    _IOC
    -0.07
    ç¼¥
    -0.07
    esten
    -0.07
    ©
    -0.07
    addir
    -0.07
    este
    -0.07
    Queryable
    -0.07
    antas
    -0.07
    POSITIVE LOGITS
     which
    0.09
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    åIJİèĢħ
    0.08
    which
    0.08
    “
    0.07
    #
    0.07
    ,,,,,,,,
    0.07
    身临åħ¶å¢ĥ
    0.07
    **
    0.07
    Activations Density 0.125%

    No Known Activations