© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 730
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ImageIcon
    -0.23
     TextAlign
    -0.23
    寡
    -0.23
     onViewCreated
    -0.23
     BufferedImage
    -0.22
     Hend
    -0.22
    -cols
    -0.21
    æĭľçĻ»
    -0.21
     Playstation
    -0.21
     där
    -0.20
    POSITIVE LOGITS
    åIJįåĪĹåīį
    0.28
    ï¼ļ"+
    0.27
    -transitional
    0.26
    'icon
    0.25
    ç½ijç«Ļåľ°åĽ¾
    0.24
    æĤ¨åIJĮæĦı
    0.24
    Ĩ
    0.24
    éĥ¨åī¯
    0.23
    CLOCKS
    0.23
    wÄĻ
    0.23
    Activations Density 3.428%

    No Known Activations