© 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. 39082
    Prev
    Next
    INDEX
    Explanations

    Christ and Marxist

    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
    cape
    -0.10
    åĴĮå¤ĦçIJĨ
    -0.09
    ights
    -0.09
    ÃŃso
    -0.09
    åĴĮä½ľçĶ¨
    -0.09
    ±
    -0.09
    åĬªåĬĽæīĵéĢł
    -0.09
    åIJĦç§įåIJĦæł·çļĦ
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    gings
    -0.08
    POSITIVE LOGITS
    лÑĭÒĽ
    0.08
    èĢħçļĦ
    0.08
    åĮĸçļĦ
    0.08
    ering
    0.07
    ean
    0.07
    ete
    0.07
    åįģ足çļĦ
    0.07
    tul
    0.06
    ÙĬÙĪÙĨ
    0.06
    pered
    0.06
    Activations Density 0.001%

    No Known Activations