© 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. 1645
    Prev
    Next
    INDEX
    Explanations

    judicial citations with years

    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
    estina
    -0.09
    èŁĨ
    -0.08
    heus
    -0.08
    _INITIALIZER
    -0.08
    usen
    -0.08
    hev
    -0.08
    entu
    -0.08
    è¿Ļåı¯æĺ¯
    -0.07
    ITAS
    -0.07
    æľĢæĸ°ç«łèĬĤ
    -0.07
    POSITIVE LOGITS
    icch
    0.06
    yk
    0.06
    asio
    0.06
    ç©·
    0.06
    ³
    0.06
    sequent
    0.06
    è¸ıå®ŀ
    0.06
    utter
    0.06
    ingo
    0.06
    boot
    0.06
    Activations Density 0.002%

    No Known Activations