© 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. 33287
    Prev
    Next
    INDEX
    Explanations

    types of

    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
    éĥ¨åĪĨçļĦ
    -0.08
    èļ
    -0.07
    ä»Ģä¹ĪçļĦ
    -0.07
    ä¸Ģç³»åĪĹ
    -0.07
     же
    -0.07
    สà¹Īวà¸Ļà¸Ĥà¸Ńà¸ĩ
    -0.07
     Sán
    -0.07
    stro
    -0.07
    ousand
    -0.07
    iless
    -0.07
    POSITIVE LOGITS
    ä¸įåIJĮç±»åŀĭçļĦ
    0.09
     namely
    0.09
    ä¸Ģç§įæĺ¯
    0.09
     types
    0.08
    strup
    0.08
     imaginable
    0.08
    ney
    0.07
     differing
    0.07
    ç±»åŀĭ
    0.07
     denen
    0.07
    Activations Density 0.176%

    No Known Activations