© 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. 41546
    Prev
    Next
    INDEX
    Explanations

    guide, article, book, information, cookbook

    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
     intelectual
    -0.07
     defended
    -0.07
    åĴĮçłĶ究
    -0.06
    åŁºç¡ĢçłĶ究
    -0.06
     intellectuals
    -0.06
    ä¸İçłĶ究
    -0.06
     historians
    -0.06
     neo
    -0.06
    intros
    -0.06
     sede
    -0.06
    POSITIVE LOGITS
     practical
    0.12
     Practical
    0.10
     actionable
    0.10
     praktische
    0.09
    ergency
    0.09
    å®ŀçĶ¨æĢ§
    0.09
    å®ŀçĶ¨çļĦ
    0.09
     ergonomic
    0.09
    è´´å¿ĥ
    0.09
    ä¸ĢæĿ¡æĿ¡
    0.09
    Activations Density 0.133%

    No Known Activations