© 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. 21356
    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
    ä¿ĿåŃĺåľ¨
    -0.08
    åŃĺåĤ¨åľ¨
    -0.07
    chie
    -0.07
    lc
    -0.07
     applied
    -0.06
    lö
    -0.06
    å§ĭèĩ³
    -0.06
     Krish
    -0.06
    ä¹ĭè¾Ī
    -0.06
    iet
    -0.06
    POSITIVE LOGITS
    ograd
    0.08
    untas
    0.07
    rlen
    0.07
    åĮĹéĿ¢
    0.07
    é¾ĻèĻİ
    0.07
    Configurer
    0.07
    çľĭæľĽ
    0.07
    gard
    0.07
     emptied
    0.07
    abouts
    0.07
    Activations Density 0.000%

    No Known Activations