© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 12
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    çļĦ带é¢Ĩ
    -0.37
     èĩªåĬ¨çĶŁæĪIJ
    -0.27
    å§Ķç»Ħç»ĩ
    -0.27
    "<?
    -0.26
    /preferences
    -0.24
    gnore
    -0.24
    仨
    -0.24
    (disposing
    -0.23
    ï¼ģ",
    -0.23
    å§Ķå®£ä¼ł
    -0.22
    POSITIVE LOGITS
    èĭ¥æĤ¨
    0.30
    æį¢åı¥è¯Ŀ
    0.29
    /stretch
    0.26
    PixelFormat
    0.25
    åĵĪåĵĪåĵĪåĵĪ
    0.24
     Playoff
    0.24
     lawy
    0.24
    /Private
    0.23
     enthus
    0.23
    iomanip
    0.23
    Activations Density 5.765%

    No Known Activations