© 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. 4130
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    ews
    -0.22
    âī«
    -0.21
    legates
    -0.21
    IRD
    -0.20
    MLS
    -0.20
    ites
    -0.20
    ARB
    -0.19
    findViewById
    -0.19
    .QueryString
    -0.19
    é¥Ķ
    -0.19
    POSITIVE LOGITS
    èİ´
    0.19
    malı
    0.17
     Hispan
    0.17
    çĿģ
    0.17
     supra
    0.17
    ä»ĩ
    0.17
    uracy
    0.17
    '>"+
    0.17
    itage
    0.17
     dipl
    0.17
    Activations Density 0.001%

    No Known Activations