© 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. 2199
    Prev
    Next
    INDEX
    Explanations

    limitations, features, developing, advancing

    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
    åĪ«æĹł
    -0.07
    æĭīæĸ¯
    -0.06
    inste
    -0.06
    Ä«v
    -0.06
     additionally
    -0.06
    kd
    -0.06
    INT
    -0.06
    èµĦæĸĻæĿ¥æºIJ
    -0.06
    åľ¨æľ¬æ¬¡
    -0.06
    ©
    -0.06
    POSITIVE LOGITS
    ä¹Łæľīå¾Īå¤ļ
    0.09
    ä¹Łä¸įå°ij
    0.08
    äºĨ许å¤ļ
    0.08
    è¿Ļæĸ¹éĿ¢çļĦ
    0.08
    ä¸įå°ij
    0.08
    å¾Īå¤ļä¸ľè¥¿
    0.08
     various
    0.08
    éĥ½ä¸įéĶĻ
    0.08
    ãģĦãĤįãģĦãĤį
    0.08
    åIJĦç§į
    0.07
    Activations Density 0.059%

    No Known Activations