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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1502
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
     Playoff
    -0.28
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.24
    人æīįéĺŁä¼į
    -0.23
    peater
    -0.23
    æľĪä¸ĭ
    -0.23
    åı¦ä¸Ģç§į
    -0.23
     FactoryBot
    -0.22
     quarterbacks
    -0.22
    æŁIJäºĽ
    -0.22
    æĶ¯çº¿ä»»åĬ¡
    -0.22
    POSITIVE LOGITS
    (Have
    0.33
    %X
    0.32
    /↵↵↵↵
    0.32
    :'.$
    0.31
    /&
    0.30
    :';↵
    0.29
    ?f
    0.28
    />.
    0.28
    '&&
    0.28
    /Dk
    0.28
    Activations Density 8.283%

    No Known Activations