© 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. 23993
    Prev
    Next
    INDEX
    Explanations

    concluding 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
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    -0.07
    izard
    -0.06
    /browse
    -0.06
    iset
    -0.06
    çļĦä¸Ĭ
    -0.06
     -
    -0.06
    以ä¸ĭæĺ¯å°ıç¼ĸ
    -0.06
    è®´æŃĮ
    -0.06
    Tooltip
    -0.05
     herk
    -0.05
    POSITIVE LOGITS
    Lastly
    0.11
     Lastly
    0.10
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.09
    æĢ»èĢĮè¨Ģä¹ĭ
    0.09
    åı¦å¤ĸä¸Ģ个
    0.09
    èĢĮè¿Ļç§į
    0.09
     Conclus
    0.08
    æľĢåIJİ
    0.08
    åĪ°æľĢåIJİ
    0.08
    æľĢåIJİæĺ¯
    0.08
    Activations Density 0.124%

    No Known Activations