© 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. 538
    Prev
    Next
    INDEX
    Explanations

    end of list items

    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
    ley
    -0.08
    èĪİ
    -0.07
    åĴĮå®ĮåĸĦ
    -0.06
     hadn
    -0.06
    ron
    -0.06
     Lumi
    -0.06
    å¨ĺå¨ĺ
    -0.06
    éĶµ
    -0.06
    æ¯Ķä»ĸ
    -0.06
    asca
    -0.06
    POSITIVE LOGITS
    è¿ĻäºĽåľ°æĸ¹
    0.08
    对äºİè¿ĻäºĽ
    0.08
    åĿĩåı¯
    0.07
    ä¹Łåı¯ä»¥æĺ¯
    0.07
    را
    0.07
    alj
    0.07
    quoi
    0.07
    æľ¬å°ı说
    0.07
     STATIC
    0.07
    ote
    0.07
    Activations Density 0.267%

    No Known Activations