© 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. 14914
    Prev
    Next
    INDEX
    Explanations

    therapy, .send, controlled, width, plan, support

    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
    ...",
    -0.07
    ency
    -0.07
    å¾·æĸ¯
    -0.07
    asta
    -0.07
    laub
    -0.06
    Åijt
    -0.06
    çļĦä¸Ģ份
    -0.06
    оÑĢÑı
    -0.06
    ä¸įä»ħåı¯ä»¥
    -0.06
    Ñīа
    -0.06
    POSITIVE LOGITS
     ↵↵
    0.07
    radas
    0.07
    wrapper
    0.07
    LOPT
    0.07
    /epl
    0.07
    çģ¯ç®±
    0.06
    arangan
    0.06
    TPL
    0.06
    ä¸įåIJĮç¨ĭ度çļĦ
    0.06
    allon
    0.06
    Activations Density 0.002%

    No Known Activations