© 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. 42018
    Prev
    Next
    INDEX
    Explanations

    Southampton, quotations, JSON, rescuer

    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
    éļĽ
    -0.07
    åij¨ä¸Ģèĩ³
    -0.06
    à¸ªà¸±à¸Ľà¸Ķาหà¹Į
    -0.06
    ,
    -0.06
    æĬĬéĴ±
    -0.06
    —a
    -0.06
    ployment
    -0.06
    istle
    -0.06
    azi
    -0.06
     Keller
    -0.06
    POSITIVE LOGITS
    èĩªå·±
    0.11
    åIJįæĢĿ
    0.08
    ostante
    0.08
    èĩªå·±æ²¡æľī
    0.08
    resents
    0.08
    penas
    0.08
    orma
    0.08
     equipments
    0.08
    à¹Ĩ
    0.07
    semble
    0.07
    Activations Density 0.003%

    No Known Activations