© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33137
    Prev
    Next
    INDEX
    Explanations

    structure, properties, responses, morphology

    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
    .utilities
    -0.07
    ikian
    -0.06
    heim
    -0.06
    为èį£
    -0.06
    æĸĩ件æĪĸ
    -0.06
    æĽ¬
    -0.06
    ä½łçļĦæīĭæľº
    -0.06
    ãģ»ãģ©
    -0.06
    ä¿¡æīĺ
    -0.06
    croft
    -0.06
    POSITIVE LOGITS
    åıĺåĮĸæĥħåĨµ
    0.10
    ä¸įåIJĮæŶ
    0.09
    ä¸įåIJĮç±»åŀĭ
    0.09
    ä¸įåIJĮçļĦ人
    0.08
    åīĸ
    0.08
    çļĦåıĺåĮĸ
    0.08
    åľ¨ä¸įåIJĮ
    0.08
    var
    0.08
    selected
    0.07
    ä¸įåIJĮè§Ĵ度
    0.07
    Activations Density 2.873%

    No Known Activations