© 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. 4353
    Prev
    Next
    INDEX
    Explanations

    factual descriptions

    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
    .leadingAnchor
    -0.23
    .mipmap
    -0.22
    ','=',$
    -0.22
    .trailingAnchor
    -0.21
    ç½ijç«Ļé¦ĸ页
    -0.21
    stants
    -0.21
    FunctionFlags
    -0.20
    ä»ĬæĹ¥å¤´æĿ¡
    -0.20
    qli
    -0.20
    ä½ıæĪ¿åħ¬ç§¯
    -0.20
    POSITIVE LOGITS
    ç«Ļ
    0.22
    é¼»
    0.21
    ESSAGE
    0.21
    anitize
    0.19
     Sebast
    0.19
     }},↵
    0.19
     |/
    0.19
    Tap
    0.19
    ãĤı
    0.19
     Guil
    0.18
    Activations Density 0.002%

    No Known Activations