© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14928
    Prev
    Next
    INDEX
    Explanations

    acetobutylicum, Beauveria, Paget disease, struvite, baler, leukemia, aflatoxin, locus, varicella, Eimeria

    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
    owani
    -0.06
    izzo
    -0.06
    Licensed
    -0.06
    olan
    -0.06
    termin
    -0.06
    owan
    -0.06
     Servi
    -0.06
     jac
    -0.06
    åľ°æľĽçĿĢ
    -0.06
    åĬ¨çļĦ
    -0.06
    POSITIVE LOGITS
    astia
    0.07
    adge
    0.07
    ayar
    0.07
    asin
    0.07
    adie
    0.07
    éĥ¨çº§
    0.06
    ä¸ĢæĿij
    0.06
    ł
    0.06
    Å¡tÄĽ
    0.06
    ¼
    0.06
    Activations Density 0.706%

    No Known Activations