© 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. 658
    Prev
    Next
    INDEX
    Explanations

    different kinds

    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
    ä¼Ĭå§ĭ
    -0.23
    潺
    -0.22
    jsonData
    -0.22
     presence
    -0.21
     equivalents
    -0.21
    mere
    -0.21
    æĽ´å¤ļçļĦæĺ¯
    -0.21
     counterparts
    -0.21
     only
    -0.21
     originals
    -0.21
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.34
     different
    0.31
    ä¸įåIJĮ
    0.31
     kinds
    0.31
    æĸ¹éĿ¢
    0.29
     aspects
    0.29
    different
    0.29
    æĸ¹éĿ¢çļĦ
    0.28
    åĽłç´ł
    0.28
    other
    0.28
    Activations Density 2.899%

    No Known Activations