© 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. 1535
    Prev
    Next
    INDEX
    Explanations

    documentation or instructions

    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
    æľīåħ³æĥħåĨµ
    -0.08
    é¢Ĩè¡Ķ
    -0.07
    ônia
    -0.07
    çļĦ缸åħ³ä¿¡æģ¯
    -0.07
    缸åħ³æĥħåĨµ
    -0.07
    Appe
    -0.07
    累累
    -0.07
    istin
    -0.07
    è¿ŀæİ¥æľī
    -0.07
    æıIJåĩºéĹ®é¢ĺ
    -0.07
    POSITIVE LOGITS
    没说
    0.08
    ush
    0.08
    身æķĻ
    0.07
    æĺİç¡®è§Ħå®ļ
    0.07
    æĮĩ示
    0.07
     clarified
    0.07
    æĺİ確
    0.07
    USH
    0.07
    ouw
    0.07
    æĺİç¡®
    0.06
    Activations Density 0.027%

    No Known Activations