© 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. 13884
    Prev
    Next
    INDEX
    Explanations

    shapes and geometry

    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
    äºĨä¸Ģå±Ĥ
    -0.07
    åľĨåľĨçļĦ
    -0.07
    æī¶çĿĢ
    -0.07
    ç»ĥåħµ
    -0.07
    åıĮåŁİ
    -0.07
    lias
    -0.07
    gol
    -0.07
    uyu
    -0.07
    åĴĮæľ¬
    -0.07
    äºĶ级
    -0.07
    POSITIVE LOGITS
     triangle
    0.11
     ABC
    0.10
     triangles
    0.10
     ÑĤÑĢеÑĥго
    0.10
    triangle
    0.10
    ä¸īè§Ĵå½¢
    0.09
    ä¸īè§Ĵå½¢çļĦ
    0.09
    ABC
    0.09
    Triangle
    0.09
     Triangle
    0.08
    Activations Density 0.018%

    No Known Activations