© 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. 8054
    Prev
    Next
    INDEX
    Explanations

    curvature and geometric shapes like triangles

    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
    ä½įç½®ä¸Ĭ
    -0.08
    Knight
    -0.08
    _mux
    -0.07
     spekt
    -0.07
    æ¸ħæ´Ĺå¹²åĩĢ
    -0.07
    éĺĢ
    -0.07
     deposit
    -0.07
    åĽŃè·¯
    -0.07
    batim
    -0.07
    ieve
    -0.07
    POSITIVE LOGITS
     exterior
    0.08
     Exterior
    0.08
     triangles
    0.08
    欧
    0.08
     interior
    0.08
    æĿ¾
    0.08
     curvature
    0.08
    ä¸īè§Ĵå½¢çļĦ
    0.07
     tabletop
    0.07
    Interior
    0.07
    Activations Density 0.003%

    No Known Activations