© 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. 22571
    Prev
    Next
    INDEX
    Explanations

    platform specific code

    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
    åĵī
    -0.07
    wald
    -0.07
    çļĦ家ä¼Ļ
    -0.07
    ä»Ļåīij
    -0.07
    ä¿Ŀåħ¨
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    æĸ°å¼Ģ
    -0.07
    .setdefault
    -0.07
    ãģ¨ãģĦãģĨæĦıåij³
    -0.07
    è·¡
    -0.06
    POSITIVE LOGITS
    ietta
    0.07
     manual
    0.07
     Manual
    0.06
    åĨĽ
    0.06
    opathy
    0.06
    箫
    0.06
    |array
    0.06
    iqué
    0.06
    avn
    0.06
    /array
    0.06
    Activations Density 0.064%

    No Known Activations