© 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. 4653
    Prev
    Next
    INDEX
    Explanations

    check or review information

    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
     ÑıкобÑĭ
    -0.08
     certain
    -0.08
    æŁIJäºĽ
    -0.08
    èĢĮå¾ĹåIJį
    -0.08
    åĴĮéĥ¨åĪĨ
    -0.07
    åĺĽ
    -0.07
     ÙĦÙĥÙĨÙĩا
    -0.07
     supposedly
    -0.07
     ÙĦÙĥÙĨÙĩ
    -0.07
     presumably
    -0.07
    POSITIVE LOGITS
     yourself
    0.12
    ä¸įè¦ģ让
    0.12
    æīįè¡Į
    0.11
    eware
    0.11
    æīį好
    0.10
     lest
    0.10
     поÑĩа
    0.10
     nhé
    0.10
    并注æĦı
    0.10
     jangan
    0.10
    Activations Density 0.166%

    No Known Activations