© 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. 46381
    Prev
    Next
    INDEX
    Explanations

    code syntax and data structures

    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
    ulg
    -0.07
    inga
    -0.07
    第äºĶå±Ĭ
    -0.06
     شأÙĨ
    -0.06
    çĶ¨åĵģ
    -0.06
    åĬ¨æľº
    -0.06
    æĬ¥å¤į
    -0.06
    tagName
    -0.06
    TagName
    -0.06
    éĻª
    -0.06
    POSITIVE LOGITS
    éĢĨ
    0.08
    çŁ¯
    0.08
     summed
    0.07
    æĢ»åĴĮ
    0.07
    累积
    0.07
    ettes
    0.07
    éĺĸ
    0.07
    åIJ¸
    0.07
    æĸ°å¹´çļĦ
    0.07
    elpers
    0.07
    Activations Density 0.012%

    No Known Activations