© 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. 10981
    Prev
    Next
    INDEX
    Explanations

    starting phrases and subsequent words

    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
    精彩åĨħ容
    -0.09
    ãĤĴå¼ķãģį
    -0.08
    uspend
    -0.07
    个人æĪĸ
    -0.07
    æĿ¥æºIJäºİç½ij绾
    -0.07
    为æĤ¨æݨèįIJ
    -0.07
    .dtd
    -0.07
    ä»·æł¼è¡Įæĥħ
    -0.07
    .lab
    -0.07
    ä»»ä½ķä¸Ģæĸ¹
    -0.07
    POSITIVE LOGITS
    æĢĿè·¯
    0.09
    çļĦæĢĿè·¯
    0.09
    çļĦæĢĿæĥ³
    0.07
    æĢ
    0.07
    æľ¬é¢ĺ
    0.07
    é¢ĺæĦı
    0.07
     basically
    0.07
     firstly
    0.07
    é¦ĸåħĪ
    0.07
     apparently
    0.07
    Activations Density 0.166%

    No Known Activations