© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 33882
    Prev
    Next
    INDEX
    Explanations

    commuting, lung, CS, TVs, billing

    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
    umpl
    -0.07
    è̦
    -0.06
    éĻ
    -0.06
    æŃ¤æĹ¶çļĦ
    -0.06
    对äºİè¿Ļ个
    -0.06
    æŃ¤æĹ¶
    -0.06
    ull
    -0.06
    ed
    -0.06
    对äºİä¸Ģ个
    -0.05
    reed
    -0.05
    POSITIVE LOGITS
    ::__
    0.09
    çļĦ人è¿ĺ
    0.09
    ä¸İåħ¶å®ĥ
    0.08
    两ä¸į误
    0.08
    æĪIJ为ä¸Ģç§į
    0.08
    cón
    0.08
    èĩªæĭħ
    0.08
    sdale
    0.08
    нге
    0.08
    è¿ĺåı¯èĥ½
    0.07
    Activations Density 0.266%

    No Known Activations