© 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. 31993
    Prev
    Next
    INDEX
    Explanations

    character codes and diy

    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
    -collar
    -0.07
    æ§ĭ
    -0.07
    vist
    -0.07
    ulis
    -0.07
    ç»Ŀ
    -0.07
    &e
    -0.07
    \admin
    -0.07
     sublicense
    -0.07
    "&
    -0.06
    ë¹Ħê°Ģ
    -0.06
    POSITIVE LOGITS
    æľīä¸īç§į
    0.08
    ãĢģ
    0.08
    æĪĸéĥ¨åĪĨ
    0.07
    ẩm
    0.07
     Diy
    0.07
    ä¸ī个人
    0.07
    opup
    0.07
     diy
    0.07
    èĴĤæĸ¯
    0.07
    ä¸ī人
    0.07
    Activations Density 0.121%

    No Known Activations