© 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. 57789
    Prev
    Next
    INDEX
    Explanations

    equation symbols and numbers

    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
     Fäh
    -0.08
    amus
    -0.08
    å°½åħ¨åĬĽ
    -0.08
    ergeb
    -0.08
     HtmlWebpackPlugin
    -0.08
    æīįåı¯
    -0.07
     oport
    -0.07
    éĻIJå®ļ
    -0.07
    æīįä¼ļæľī
    -0.07
    æ¡¥åĮº
    -0.07
    POSITIVE LOGITS
     satisfies
    0.10
    满足
    0.10
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.09
    èĥ½æ»¡è¶³
    0.08
    åı¯ä»¥æ»¡è¶³
    0.08
    符åIJĪè¦ģæ±Ĥ
    0.08
    满足äºĨ
    0.08
     satisfy
    0.08
    滿足
    0.08
    .Verify
    0.07
    Activations Density 0.011%

    No Known Activations