© 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. 59856
    Prev
    Next
    INDEX
    Explanations

    old value

    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
    _FRAGMENT
    -0.09
    åıªè¦ģèĥ½
    -0.07
    urch
    -0.07
    åįĹèĩ³
    -0.07
     altına
    -0.07
     fór
    -0.07
     assorted
    -0.07
    orna
    -0.07
    éķ¿æľŁçļĦ
    -0.07
     abandoned
    -0.07
    POSITIVE LOGITS
    åIJĮä¸Ģ
    0.10
    åIJĮä¸Ģ个
    0.09
    åľ¨åIJĮä¸Ģ
    0.09
    è¿Ń
    0.08
    马ä¸Ĭ
    0.07
    åĪļåĪļ
    0.07
    åĪļ
    0.07
    åľ¨åIJĮ
    0.07
    æĽ´æĸ°
    0.07
    å¯¹æľ¬æ¬¡
    0.07
    Activations Density 0.021%

    No Known Activations