© 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. 30020
    Prev
    Next
    INDEX
    Explanations

    copyright, license

    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
    -0.09
    ä¸į管æĺ¯
    -0.09
     Maybe
    -0.09
    maybe
    -0.08
     tremendously
    -0.08
    ä¸įä»ħä»ħæĺ¯
    -0.08
     somehow
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
     maybe
    -0.07
    缴æİ¥æĪĸ
    -0.07
    POSITIVE LOGITS
    éģ¨
    0.09
    راÙģÛĮ
    0.07
    ATIV
    0.07
    åĵŃç¬ijä¸įå¾Ĺ
    0.06
    ×ķ×ij×Ķ
    0.06
    ä½Ļ次
    0.06
    ervative
    0.06
     лиÑĪÑĮ
    0.06
    æĥħå½¢çļĦ
    0.06
    ']/
    0.06
    Activations Density 0.001%

    No Known Activations