© 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. 44720
    Prev
    Next
    INDEX
    Explanations

    objective is

    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
    为主è¦ģ
    -0.08
    åıªä»£è¡¨
    -0.07
    ä¸įåı¯æĢķ
    -0.07
    羣æŃ£æĪIJ为
    -0.07
    ä½ľä¸ºä¸ŃåĽ½
    -0.07
    åĽłä¸ºå®ĥ
    -0.07
    ä½ľä¸ºä¸Ģ个
    -0.07
    çļĦéĩįè¦ģä½ľçĶ¨
    -0.07
    ä¹Łä¸įåı¯èĥ½
    -0.07
    åħĪä»İ
    -0.07
    POSITIVE LOGITS
     adalah
    0.13
    çļĦæĺ¯
    0.13
    à¸Ħืà¸Ńà¸ģาร
    0.12
    à¸Ħืà¸Ń
    0.12
     is
    0.12
     ialah
    0.11
    åľ¨äºİ
    0.11
     ê²ĥìĿĢ
    0.10
    ä¹ĭä¸Ģæĺ¯
    0.10
    çļĦè¯Ħä»·æĺ¯
    0.10
    Activations Density 0.237%

    No Known Activations