© 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. 44005
    Prev
    Next
    INDEX
    Explanations

    main, primary, starter

    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
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    -0.08
    为åħĪ
    -0.07
    vale
    -0.07
    -sided
    -0.07
    个人è¡Į为
    -0.07
    åIJĦå¼ıåIJĦ
    -0.06
    hum
    -0.06
    hesion
    -0.06
    Hum
    -0.06
     Woj
    -0.06
    POSITIVE LOGITS
    /main
    0.15
    (primary
    0.14
    /core
    0.13
    /Main
    0.13
    (main
    0.12
     primary
    0.12
    primary
    0.11
    主
    0.11
    åĴĮéĩįçĤ¹
    0.11
     اصÙĦÛĮ
    0.11
    Activations Density 0.165%

    No Known Activations