© 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. 52184
    Prev
    Next
    INDEX
    Explanations

    name of idea

    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
    nict
    -0.07
    ç¼Ń
    -0.07
    åĪ°æľĢåIJİ
    -0.07
     Atra
    -0.07
    ilde
    -0.06
    ilder
    -0.06
     Chall
    -0.06
    ynu
    -0.06
    ivre
    -0.06
    gers
    -0.06
    POSITIVE LOGITS
    åĪļæīį
    0.09
    åĪļåĪļ
    0.08
    å·²ç»ıä¸įæĺ¯
    0.08
    好ä¸į容æĺĵ
    0.08
    å·²ç»ıç»ĵæĿŁ
    0.08
    以åIJİ
    0.08
    åīĽæīį
    0.08
    è¿Ļä¸Ģ个
    0.07
    å·²ç»ıå®ĮæĪIJ
    0.07
    opic
    0.07
    Activations Density 0.227%

    No Known Activations