© 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. 40345
    Prev
    Next
    INDEX
    Explanations

    crypt library, full media, rtl text, code line

    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
     appunto
    -0.12
    ä¸ĭåIJĮ
    -0.09
    管çIJĨçŃī
    -0.09
    æĥħåĨµçŃī
    -0.08
    设å¤ĩçŃī
    -0.08
    æ³ķçŃī
    -0.08
    æľįåĬ¡çŃī
    -0.08
    åIJİèĢħ
    -0.08
    æ´»åĬ¨çŃī
    -0.08
    åħ¬åı¸çŃī
    -0.08
    POSITIVE LOGITS
     tehát
    0.07
     ugyanis
    0.07
     обаÑĩе
    0.07
    ãģ¨ãģĦãģĨãģ¨
    0.07
    æľ¬æ¥¼
    0.07
     congratulations
    0.06
     tellement
    0.06
    ä¸įä»ħèĥ½å¤Ł
    0.06
    )(((
    0.06
    天éªĦ
    0.06
    Activations Density 0.300%

    No Known Activations