© 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. 43452
    Prev
    Next
    INDEX
    Explanations

    following followed by list items

    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
    åı¯è¨Ģ
    -0.07
    itial
    -0.07
    -0.07
    çIJ³å¨ľ
    -0.07
    éħįç½®æĸ¹éĿ¢
    -0.07
    auc
    -0.07
    è£Ķ
    -0.07
    裡çļĦ
    -0.07
    ä¸Ĭä¸į
    -0.07
    nin
    -0.07
    POSITIVE LOGITS
     prins
    0.07
    ç¼ĵ
    0.07
    agraph
    0.07
    жиÑĤ
    0.07
    ìĦŃ
    0.06
    stell
    0.06
    áĢĶáĢºáĢ¸
    0.06
    人寿
    0.06
    uvia
    0.06
    oops
    0.06
    Activations Density 0.016%

    No Known Activations