© 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. 20071
    Prev
    Next
    INDEX
    Explanations

    % or percent for concentrations

    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
     succesfully
    -0.08
    elit
    -0.07
    umer
    -0.07
    ãģ´
    -0.07
     Ñīи
    -0.07
    -Mart
    -0.07
    ä¸įè¦ģå¿ĺäºĨ
    -0.07
    PREFIX
    -0.07
    ÏĥÏĦη
    -0.07
    çŁ¥éģĵä½ł
    -0.07
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.08
    aved
    0.07
    åIJ«
    0.06
    ãģ°ãģĭãĤĬ
    0.06
     ment
    0.06
    ulated
    0.06
    åĩĨå¤ĩ好çļĦ
    0.06
    æľīèī²
    0.06
    ened
    0.06
    åİļ
    0.06
    Activations Density 0.044%

    No Known Activations