© 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. 26274
    Prev
    Next
    INDEX
    Explanations

    text following punctuation

    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
    èѬå¦Ĥ
    -0.10
    å¦ĤåĪĿ
    -0.09
    æ¯Ķå¦Ĥ说
    -0.08
    å¦Ĥ对
    -0.08
     напÑĢ
    -0.07
    æĩ
    -0.07
    æ¯Ķå¦Ĥ
    -0.07
    æĬ
    -0.07
    å¦Ĥçİī
    -0.07
    å¦Ĥ
    -0.07
    POSITIVE LOGITS
    åıĪå¦Ĥ
    0.14
     Similarly
    0.09
    ä¸įèĥľ
    0.08
     similarly
    0.08
    ä¹Łåı¯ä»¥æĺ¯
    0.08
     ìĿ´ì²ĺëŁ¼
    0.08
    åıĪåĥı
    0.07
    tria
    0.07
    æĢ»ä¹ĭ
    0.07
    enan
    0.07
    Activations Density 0.141%

    No Known Activations