© 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. 1543
    Prev
    Next
    INDEX
    Explanations

    news

    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
     (
    -0.31
    æīĢ
    -0.29
    èµ°åĬ¿åĽ¾
    -0.28
    æĪĸèĢħ说
    -0.27
    çļĦéĤ£ä¸Ģ
    -0.27
    æīĢæıIJä¾ĽçļĦ
    -0.26
    çļĦéĤ£ç§į
    -0.25
    以åıĬ
    -0.25
     "
    -0.24
    æĪĸèĢħæĺ¯
    -0.24
    POSITIVE LOGITS
    .BASELINE
    0.36
    ä¸īç§įèģĮä¸ļ
    0.35
    ãİŀ
    0.33
    ãİı
    0.32
     embod
    0.32
    /*↵
    0.32
    -Trump
    0.32
     LENG
    0.30
    ä¸ŃåĽ½ç½ij游
    0.30
     ìĿ´ëłĩ
    0.30
    Activations Density 9.299%

    No Known Activations