© 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. 47199
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.14
    zelf
    -0.10
    µ
    -0.09
    лио
    -0.08
    bsites
    -0.08
    uva
    -0.08
    UTTON
    -0.08
    ÄįÃŃ
    -0.08
    jÅ¡ÃŃ
    -0.08
    uvi
    -0.08
    POSITIVE LOGITS
    //*
    0.10
    и
    0.09
    âĢ¦*
    0.08
    ãģ¯ãģĦãģijãģªãģĦ
    0.08
    ...*
    0.08
    ами
    0.07
    eil
    0.07
    ity
    0.07
    à¥ĩ
    0.07
    าà¸Ĺ
    0.07
    Activations Density 0.079%

    No Known Activations