© 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. 19885
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    cula
    -0.09
    ä¸įæĥĬ
    -0.09
    ÑĢовок
    -0.08
    翼翼
    -0.08
    请çĻ»å½ķ
    -0.08
    iseerd
    -0.08
    anghai
    -0.08
    ymm
    -0.08
    请åĬł
    -0.08
    /sources
    -0.08
    POSITIVE LOGITS
    ä¸įå®ĮçļĦ
    0.07
    ÙĮ
    0.07
    æĦŁåįģ足
    0.07
    æĭ¥
    0.07
    åIJĹ
    0.06
    heureusement
    0.06
    çļĦåIJĹ
    0.06
    大
    0.06
    ',//
    0.06
    åĺĽ
    0.06
    Activations Density 0.074%

    No Known Activations