© 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. 55544
    Prev
    Next
    INDEX
    Explanations

    matrices, graphs, rings, manifold

    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
    ata
    -0.07
    åĤ²
    -0.06
    è¿Ļæł·ä¸Ģ个
    -0.06
    è¿Ļæł·çļĦä¸Ģ个
    -0.06
    hto
    -0.06
     Ñģиг
    -0.06
    re
    -0.06
    ¯
    -0.06
    åľ¨åĽ½å¤ĸ
    -0.06
    ÄĹ
    -0.06
    POSITIVE LOGITS
    atten
    0.08
    æĢ»ä½ĵè¦ģæ±Ĥ
    0.08
    urkan
    0.08
    ahal
    0.07
    æĪĺæ³ķ
    0.07
    ĵĺ
    0.07
    ê·¼
    0.07
    rund
    0.07
    zell
    0.07
    fram
    0.06
    Activations Density 0.263%

    No Known Activations