© 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. 19215
    Prev
    Next
    INDEX
    Explanations

    arithmetic symbols and equations

    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
    åĭĩå¾Ģ缴åīį
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    äºĭåįĬåĬŁåĢį
    -0.06
    ä¸įå®ĮçļĦ
    -0.06
    -0.06
    身临åħ¶å¢ĥ
    -0.06
    å¾Ĺä½ı
    -0.06
    两åѦä¸Ģåģļ
    -0.06
    åIJĦç§įåIJĦæł·çļĦ
    -0.06
    POSITIVE LOGITS
    èĩªå·±
    0.14
    èĩªå·±æ²¡æľī
    0.12
    èĩªå·±è¢«
    0.12
    wards
    0.11
    urator
    0.10
    èĩªå·±èº«ä¸Ĭ
    0.10
    urations
    0.09
    empre
    0.09
    zinho
    0.09
    èĩªå·±æľī
    0.09
    Activations Density 0.356%

    No Known Activations