© 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. 56930
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or notation

    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
    loys
    -0.08
    reeze
    -0.08
    ETTO
    -0.08
    ENTO
    -0.08
     Mattis
    -0.08
    ãģ¨è©±
    -0.08
    дика
    -0.08
    åľ¨åľºçļĦ
    -0.07
    inare
    -0.07
    ogle
    -0.07
    POSITIVE LOGITS
    åįĹè¡Ĺ
    0.07
    reet
    0.07
    榨
    0.07
    گاÙĩ
    0.07
    ä¸Ģ个人çļĦ
    0.07
     his
    0.06
    pite
    0.06
    ç»Ļä»ĸçļĦ
    0.06
    coa
    0.06
    æŃ¢
    0.06
    Activations Density 0.002%

    No Known Activations