© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17196
    Prev
    Next
    INDEX
    Explanations

    differences

    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
    ä¸į失
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    elev
    -0.08
    itu
    -0.08
    wad
    -0.08
    amax
    -0.07
    åIJĦç§į
    -0.07
    hud
    -0.07
    ä¸į移
    -0.07
    åIJĦç§įéĹ®é¢ĺ
    -0.07
    POSITIVE LOGITS
     differences
    0.13
     difference
    0.12
     perbedaan
    0.12
    æĪªçĦ¶ä¸įåIJĮ
    0.12
     differing
    0.12
    ãģ®éģķãģĦ
    0.11
    åIJĦèĩª
    0.11
    ä¸Ģ个æĺ¯
    0.11
    æĪªçĦ¶ä¸įåIJĮçļĦ
    0.11
     Perbedaan
    0.11
    Activations Density 0.065%

    No Known Activations