© 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. 9326
    Prev
    Next
    INDEX
    Explanations

    fractions and division

    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
    acor
    -0.08
    ucha
    -0.08
    æ±Ģ
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    追éĢIJ
    -0.07
    aczy
    -0.07
    azo
    -0.07
    /bin
    -0.07
    ÙĪÙĬد
    -0.07
    \\.
    -0.06
    POSITIVE LOGITS
    çĬ¶åħĥ
    0.07
    gol
    0.07
    umos
    0.07
    legg
    0.06
    tus
    0.06
    æ²½
    0.06
    tant
    0.06
    é¦ĸ页
    0.06
     दरà¥į
    0.06
     dụ
    0.06
    Activations Density 0.018%

    No Known Activations