© 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. 32825
    Prev
    Next
    INDEX
    Explanations

    same

    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
    _PIXEL
    -0.07
    ä½ķçŃī
    -0.07
    óp
    -0.07
    ç¦Ħ
    -0.06
    åĴĮçĶ°
    -0.06
    ä¹ĭé«ĺ
    -0.06
    æĺ¥æļĸ
    -0.06
     tightly
    -0.06
    udos
    -0.06
     char
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ģ
    0.12
    åIJĮä¸Ģ个
    0.11
    åľ¨ä¸įåIJĮ
    0.11
    åľ¨ä¸įåIJĮçļĦ
    0.11
    åIJĮãģĺ
    0.11
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.10
    åIJĮæł·çļĦ
    0.10
     åIJĮãģĺ
    0.10
    缸åIJĮçļĦ
    0.09
    same
    0.09
    Activations Density 0.110%

    No Known Activations