© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 6947
    Prev
    Next
    INDEX
    Explanations

    questions about choice

    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
    Negative Logits
    ä¸įä¸Ģå®ļæĺ¯
    -0.10
    ä¸įä¸Ģå®ļ
    -0.09
    æļĤæľª
    -0.08
    æľªå¿ħ
    -0.08
    并ä¸įéļ¾
    -0.08
    足ä¸įåĩº
    -0.08
     WITHOUT
    -0.08
    ä¸įæIJŀ
    -0.08
    足ä¸įåĩºæĪ·
    -0.08
    ä¸įè¦ģå¿ĺäºĨ
    -0.08
    POSITIVE LOGITS
    åıĸèĢĮ代ä¹ĭ
    0.12
     ÐĹаÑĤо
    0.12
     заÑĤо
    0.11
    åį³ä¾¿å¦ĤæѤ
    0.09
    ä¾ĭå¤ĸ
    0.09
    è¡¥æķij
    0.09
    æĥŁä¸Ģ
    0.09
    尽管å¦ĤæѤ
    0.09
     tampoco
    0.09
    å¾Ĵ
    0.09
    Activations Density 0.318%

    No Known Activations