© 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. 14448
    Prev
    Next
    INDEX
    Explanations

    medical conditions, species, aviation, tumors, profile

    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
    vens
    -0.07
     pomp
    -0.07
    валÑĮ
    -0.07
    insky
    -0.07
    oron
    -0.07
    UnitTest
    -0.07
     Blaze
    -0.07
     Nai
    -0.07
    åŃĺ
    -0.06
    Ŀ
    -0.06
    POSITIVE LOGITS
    åľ¨è¿Ļæĸ¹éĿ¢
    0.10
    è¿Ļæĸ¹éĿ¢çļĦ
    0.10
    ä¸İæѤ
    0.10
    åľ¨è¿Ļç§į
    0.10
    åľ¨è¿Ļæł·çļĦ
    0.09
     regarding
    0.08
    åĽłä¸ºè¿Ļ个
    0.08
    ä»İè¿Ļ个
    0.08
    对è¿ĻäºĽ
    0.08
    对æѤ
    0.08
    Activations Density 1.009%

    No Known Activations