© 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. 37600
    Prev
    Next
    INDEX
    Explanations

    things taught

    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
    åľ¨å·¥ä½ľä¸Ĭ
    -0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
    INLINE
    -0.07
    æĶĺ
    -0.07
    èĥ½æī¿åıĹ
    -0.07
    ัย
    -0.07
     alb
    -0.07
    èĩªè¨Ģ
    -0.07
     INLINE
    -0.07
    ä¹Łåı¯ä»¥æĺ¯
    -0.06
    POSITIVE LOGITS
    çģĮè¾ĵ
    0.09
    çĪ±åĽ½ä¸»ä¹īæķĻèĤ²
    0.08
     often
    0.08
    éĢļ常ä¼ļ
    0.07
    ä¼łæİĪ
    0.07
    çļĦæĥħæĻ¯
    0.07
    å®ĪåĪĻ
    0.07
    eldom
    0.07
     usually
    0.07
    离家
    0.07
    Activations Density 0.068%

    No Known Activations