© 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. 63679
    Prev
    Next
    INDEX
    Explanations

    blown off, scared silly, bred out

    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
    less
    -0.08
    adamente
    -0.08
    ulton
    -0.07
    LESS
    -0.07
    unky
    -0.07
    äºİæѤ
    -0.07
    æ°§åĮĸ碳
    -0.07
    ÙĪØ®
    -0.07
    amente
    -0.07
    varo
    -0.07
    POSITIVE LOGITS
    å®ĮåIJİ
    0.09
    个ä¸įåģľ
    0.09
    å¾ĹæĽ´
    0.09
    èµ·æĿ¥
    0.09
    è¿ĩ头
    0.09
    æŃª
    0.09
    å®Įä¹ĭåIJİ
    0.09
    ä¸Ĭçĺ¾
    0.09
    èµ·ä¾Ĩ
    0.08
    å¾Ĺ好
    0.08
    Activations Density 0.010%

    No Known Activations