© 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. 46691
    Prev
    Next
    INDEX
    Explanations

    code punctuation or variables

    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
    æĭ¯
    -0.08
    æĢ»ç»ĵå¦Ĥä¸ĭ
    -0.08
    ä»ĸèĩªå·±çļĦ
    -0.08
    à¦ķà§įষà§ĩ
    -0.08
    æ¯Ķè¾ĥ严éĩį
    -0.07
    ä¾µçĬ¯äºĨæĤ¨çļĦ
    -0.07
    ÑģÑĥÑĢ
    -0.07
    ogi
    -0.07
    ilet
    -0.07
    ltra
    -0.07
    POSITIVE LOGITS
    ẩm
    0.07
    IMIT
    0.07
    ód
    0.07
    é¼İ
    0.07
    Wed
    0.07
    åĬĽéĩı
    0.07
    éĥ¨éŨåĴĮ
    0.07
     #__
    0.06
    ÅĪ
    0.06
    _Static
    0.06
    Activations Density 0.056%

    No Known Activations