© 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. 41400
    Prev
    Next
    INDEX
    Explanations

    into programming and tech topics

    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
    éĤ£æĺ¯æĪij
    -0.08
    éĤ£æĺ¯åĽłä¸º
    -0.07
    åľ¨äº¬
    -0.07
    rames
    -0.07
    aÅĤ
    -0.07
    åľ¨èĬ±
    -0.07
    å¦Ĥçİī
    -0.06
    isz
    -0.06
    ISC
    -0.06
    Covid
    -0.06
    POSITIVE LOGITS
    è¿Ļä¸ªä¸ľè¥¿
    0.08
    并积æŀģ
    0.08
    orses
    0.08
    è¿Ļ个è¡Įä¸ļ
    0.08
     basics
    0.08
    è¿ĻæĿ¡è·¯
    0.08
    è¿Ļ两ç§į
    0.07
     this
    0.07
    è¿Ļç§įä¸ľè¥¿
    0.07
     Basics
    0.07
    Activations Density 1.023%

    No Known Activations