© 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. 8050
    Prev
    Next
    INDEX
    Explanations

    patent describes

    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
    atk
    -0.08
    rent
    -0.07
    å¤ļå°ij人
    -0.07
    æĤ¨æīĢåľ¨çļĦä½įç½®
    -0.07
    attended
    -0.07
     diken
    -0.07
    isure
    -0.07
    ä¸Ģ说
    -0.07
    grade
    -0.07
    ubile
    -0.07
    POSITIVE LOGITS
    's
    0.09
    iffer
    0.08
    ’s
    0.07
    ‘s
    0.07
    &A
    0.07
    tschaft
    0.06
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    0.06
    _MAXIMUM
    0.06
    allback
    0.06
    带é¢Ĩä¸ĭ
    0.06
    Activations Density 0.001%

    No Known Activations