© 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. 11784
    Prev
    Next
    INDEX
    Explanations

    multiple interfaces or cells

    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
    รà¹Īวมà¸ģัà¸ļ
    -0.08
    åĩ¡äºĭ
    -0.07
    iori
    -0.07
    ä¸İåIJĦ
    -0.07
    ena
    -0.07
    pure
    -0.07
    onda
    -0.06
    æĹłå¤Ħä¸įåľ¨
    -0.06
    èĵ¬
    -0.06
    çļĦä¸Ģ款
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸įåIJĮçļĦ
    0.17
    åľ¨åIJĮä¸Ģ
    0.15
    ä¸įåIJĮçļĦ
    0.15
    åIJĮä¸Ģ个
    0.14
    ä¸įåIJĮ
    0.14
     unterschied
    0.14
    æľīä¸įåIJĮçļĦ
    0.14
    æĺ¯åIJĮ
    0.13
    åIJĮä¸Ģ
    0.13
     differing
    0.13
    Activations Density 0.237%

    No Known Activations