© 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. 9441
    Prev
    Next
    INDEX
    Explanations

    distance from

    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
    utang
    -0.08
    åįĬåľº
    -0.08
    Ł
    -0.07
    éné
    -0.07
    jobb
    -0.07
    让åIJĮåѦ们
    -0.07
    egy
    -0.07
    तर
    -0.07
    æĶ¾çľ¼
    -0.07
    eldon
    -0.07
    POSITIVE LOGITS
    ä¸Ńå¿ĥ
    0.07
    åİŁçĤ¹
    0.07
     center
    0.06
    ä¸Ńå¿ĥçŃī
    0.06
    éľ²éĿ¢
    0.06
     distant
    0.06
    åı¦ä¸Ģ
    0.06
    .NewReader
    0.06
    ÑģÑĤоиÑĤ
    0.06
    ä¸Ńå¿ĥåŁİå¸Ĥ
    0.06
    Activations Density 0.056%

    No Known Activations