© 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. 50637
    Prev
    Next
    INDEX
    Explanations

    science, math, code, biology, event announcements

    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
    itation
    -0.09
    itations
    -0.09
    itato
    -0.08
    itat
    -0.08
    conte
    -0.08
    abal
    -0.08
    itated
    -0.07
    ibert
    -0.07
    asso
    -0.07
     McGr
    -0.07
    POSITIVE LOGITS
    ายà¸Ļ
    0.07
    eda
    0.07
    øre
    0.07
     jub
    0.06
    jad
    0.06
    бÑĥÑĤ
    0.06
    iban
    0.06
    è¢Ń
    0.06
    ä¸įåĬ¨
    0.06
    жеÑĤе
    0.06
    Activations Density 0.017%

    No Known Activations