© 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. 39843
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals and limits

    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
     Holden
    -0.07
    æĢĢæĬ±
    -0.07
    azar
    -0.07
    _defaults
    -0.07
    è¿ŀçݯ
    -0.07
    æĻ©
    -0.07
     Gow
    -0.07
    èĨĽ
    -0.07
    æĥĬå¿ĥåĬ¨
    -0.07
    åĶIJ人
    -0.06
    POSITIVE LOGITS
    íĬ¼
    0.07
    ess
    0.07
    UTH
    0.06
    ÅŁti
    0.06
     поÑģи
    0.06
    ëĭĺê»ĺìĦľ
    0.06
    amenti
    0.06
    неÑģ
    0.06
    çİĽçijĻ
    0.06
    yper
    0.06
    Activations Density 0.003%

    No Known Activations