© 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. 20023
    Prev
    Next
    INDEX
    Explanations

    setting terms and technical description

    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
    ä¸įåıª
    -0.07
    责任å¿ĥ强
    -0.07
    浦
    -0.07
    acol
    -0.07
    TRL
    -0.07
    intis
    -0.07
    丰å¯Įå¤ļ彩çļĦ
    -0.07
    并ä¸įéļ¾
    -0.07
    ä»įæľª
    -0.06
    æŃ£æĺ¯åľ¨
    -0.06
    POSITIVE LOGITS
     anymore
    0.08
    èĢĮæĺ¯
    0.08
    áĥĺáĥł
    0.07
     directly
    0.07
    éĽªä¸Ń
    0.07
     pÅĻÃŃmo
    0.07
     بÙĦÚ©Ùĩ
    0.07
    leo
    0.07
     melainkan
    0.07
    åĪĹ
    0.07
    Activations Density 0.006%

    No Known Activations