© 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. 27147
    Prev
    Next
    INDEX
    Explanations

    relation between

    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
    endorf
    -0.08
    INO
    -0.07
    è¿ĺæľīä¸Ģ个
    -0.07
    ropol
    -0.07
     statistic
    -0.06
    иÑģÑĤо
    -0.06
    everyone
    -0.06
    roup
    -0.06
    jel
    -0.06
     competitive
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.11
    æĺ¯ä¸ĢäºĽ
    0.11
     allerlei
    0.11
    åIJĦç§į
    0.10
    çļĦåIJĦç±»
    0.10
    çļĦåIJĦç§į
    0.10
    Various
    0.10
    éĥ½æĺ¯ä¸ĢäºĽ
    0.10
     assorted
    0.10
    åIJĦå¼ıåIJĦæł·çļĦ
    0.10
    Activations Density 0.282%

    No Known Activations