© 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. 28459
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¯Ķæ¯Ķ
    -0.09
    assist
    -0.08
    ä¹Łä¸įåı¯
    -0.08
    åĪĨæĺİ
    -0.08
    ধà§įয
    -0.07
    istar
    -0.07
    inker
    -0.07
    ovy
    -0.07
    oup
    -0.07
    (&(
    -0.07
    POSITIVE LOGITS
    å¦Ŀ
    0.07
    æĽ²æ±Ł
    0.06
    eder
    0.06
     Rew
    0.06
    ç»Ļ人以
    0.06
    sud
    0.06
    ãĤĥ
    0.06
    TD
    0.06
     rewritten
    0.06
    åѦåĪ°äºĨå¾Īå¤ļ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.