© 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. 60685
    Prev
    Next
    INDEX
    Explanations

    obtain a copy of the license

    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
    riba
    -0.09
    elh
    -0.09
    /jav
    -0.08
     sekal
    -0.08
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    zac
    -0.08
    оÑģÑģ
    -0.08
    ாள
    -0.08
    arczy
    -0.08
    inos
    -0.08
    POSITIVE LOGITS
    le
    0.07
    re
    0.06
    å¼Ģå±ķ
    0.06
    unt
    0.06
    åľ¨å¤©
    0.06
     involuc
    0.05
    æľī声
    0.05
    èĢĮ
    0.05
    ek
    0.05
     Rol
    0.05
    Activations Density 0.001%

    No Known Activations