© 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. 37788
    Prev
    Next
    INDEX
    Explanations

    documents and files

    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
    ξηÏĤ
    -0.08
    为æĤ¨æݨèįIJ
    -0.07
    æݨèįIJæľ¬ä¹¦
    -0.07
    _SB
    -0.07
    稿件æĿ¥æºIJ
    -0.07
    ezo
    -0.07
    æĬ½æŁ¥æ£ĢæŁ¥
    -0.07
     Interrupt
    -0.07
    æĸ°ä¹¦æݨèįIJ
    -0.07
    书åıĭ
    -0.07
    POSITIVE LOGITS
    çĶµåŃIJçīĪ
    0.12
    åī¯æľ¬
    0.12
     copies
    0.11
    ä¸Ģå¼ı
    0.11
     files
    0.11
    ä¸Ģ份
    0.11
    æŃ£æľ¬
    0.11
    çŃīèµĦæĸĻ
    0.11
     documents
    0.11
     downloaded
    0.11
    Activations Density 0.550%

    No Known Activations