© 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. 736
    Prev
    Next
    INDEX
    Explanations

    late, point, border, darkness

    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
    åģ¥
    -0.10
    æĹłçĹķ
    -0.09
    åħ¨åı°
    -0.09
    ç»ı常ä¼ļ
    -0.08
    壹
    -0.08
    lou
    -0.08
    é«ĺé¢ij
    -0.08
     useMemo
    -0.08
    éļıåı£
    -0.08
    æĹłè¨Ģ
    -0.08
    POSITIVE LOGITS
    éĿ©åij½çļĦ
    0.09
    è¿ĩ渡
    0.09
    åŃķèĤ²
    0.08
    èµĦæľ¬ä¸»ä¹ī
    0.08
    æij¸ç´¢
    0.08
    éĿ©åij½
    0.08
    èIJ½åIJİ
    0.08
     stages
    0.07
    å¥ĭæĸĹ缮æłĩ
    0.07
    Transition
    0.07
    Activations Density 0.005%

    No Known Activations