© 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. 33480
    Prev
    Next
    INDEX
    Explanations

    this is

    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
    ä¸ŃåŃ¦ä¹ł
    -0.08
    ujur
    -0.07
    åIJīæĸ¯
    -0.07
    ä¿¡æģ¯ç½ij
    -0.07
    ünst
    -0.07
     ÑĢазÑĥм
    -0.07
    skom
    -0.07
     Heim
    -0.07
    åĩºå¸ŃäºĨ
    -0.07
    icrosoft
    -0.06
    POSITIVE LOGITS
    tez
    0.07
    ichel
    0.07
    Ļ
    0.07
    ndata
    0.07
    æıIJåĩº
    0.07
    terer
    0.07
     tez
    0.07
    åĨ²åĨ²
    0.07
    arding
    0.06
    y
    0.06
    Activations Density 0.001%

    No Known Activations