© 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. 24697
    Prev
    Next
    INDEX
    Explanations

    special emphasis or extent

    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
    æ¯Ķä½ł
    -0.09
    æľīå¾Ī大çļĦ
    -0.07
    ÅĤu
    -0.07
    reat
    -0.07
    /from
    -0.07
    oidal
    -0.07
    riere
    -0.07
    rtle
    -0.07
    ëĭĪëĭ¤
    -0.07
     Seri
    -0.07
    POSITIVE LOGITS
    çļĦè¿ĺæľī
    0.13
    çļĦæĺ¯
    0.12
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.09
    æľī趣çļĦæĺ¯
    0.09
     also
    0.09
     ÑĤакже
    0.08
     juga
    0.08
    ãģªãģ®ãģ¯
    0.08
    注æĦıçļĦæĺ¯
    0.08
    åĢĴæĺ¯
    0.08
    Activations Density 0.068%

    No Known Activations