© 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. 7109
    Prev
    Next
    INDEX
    Explanations

    closing 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
    Negative Logits
    è¿Ļä¸įä»ħ
    -0.09
    ä¸įä»ħä»ħæĺ¯
    -0.09
    ä¸įä»ħ
    -0.08
    æĹłè®ºæĺ¯åľ¨
    -0.08
    ä¸įåĥħ
    -0.08
    ä¸įä»ħåľ¨
    -0.08
    ä¸įä½Ĩ
    -0.07
    eland
    -0.07
    ä¸įä»ħå¦ĤæѤ
    -0.07
    ä¸įä»ħæĺ¯
    -0.07
    POSITIVE LOGITS
    æĢ»ä½ĵæĿ¥è¯´
    0.11
    æĢ»ä½ĵèĢĮè¨Ģ
    0.10
     ê·¸ëŀĺëıĦ
    0.10
     Overall
    0.09
    AtA
    0.09
    æĢ»ä½ĵä¸Ĭ
    0.09
    主è¦ģè¿ĺæĺ¯
    0.08
     overall
    0.08
    æķ´ä½ĵä¸Ĭ
    0.08
    overall
    0.08
    Activations Density 0.154%

    No Known Activations