© 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. 7124
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or decimal points

    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
    ä¸Ģä¹Ŀ
    -0.09
    engel
    -0.07
    å¾ĢæľŁåĽŀ顾
    -0.06
     nineteen
    -0.06
    äºĶæĺ¯
    -0.06
    念念ä¸įå¿ĺ
    -0.06
    åįģä¸ĢæľĪ
    -0.06
    åĽĽæĺ¯
    -0.06
    endre
    -0.06
     period
    -0.06
    POSITIVE LOGITS
    inkin
    0.09
    iches
    0.08
    .fits
    0.08
    æĬĢæľ¯ä¸ĵä¸ļ
    0.08
    åĪĨ许
    0.08
    æĸĩç«łäºĨ
    0.08
    èµĦè´¨è¯ģ书
    0.08
    PressEvent
    0.07
    åħĥ人æ°ijå¸ģ
    0.07
    cian
    0.07
    Activations Density 0.159%

    No Known Activations