© 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. 50387
    Prev
    Next
    INDEX
    Explanations

    zhangtiande

    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
    åĴĮ第
    -0.07
    -addon
    -0.06
    夫妻
    -0.06
    ç»ıçIJĨæĭĽèģĺ
    -0.06
    itemid
    -0.06
    æīŃ头
    -0.06
    建ç«ĭåľ¨
    -0.06
    egram
    -0.06
    夫妻俩
    -0.06
    ython
    -0.06
    POSITIVE LOGITS
    çļĦåįļ客
    0.10
    çģ
    0.08
    ahuan
    0.07
    @qq
    0.07
    नà¥įन
    0.07
    ãģº
    0.07
    raphe
    0.07
    study
    0.07
     study
    0.07
    aum
    0.07
    Activations Density 0.038%

    No Known Activations