© 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. 996
    Prev
    Next
    INDEX
    Explanations

    structured technical text

    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
    æ¯ıæĹ¥ç»ıæµİ
    -0.23
    çİ¢
    -0.22
    ç¼Ĵ
    -0.20
    ekyll
    -0.20
     Lexus
    -0.20
    èĴº
    -0.20
    åħ¨åĬĽæīĵéĢł
    -0.20
    æļ´æ¶¨
    -0.20
    iciel
    -0.19
    å¾Ī满æĦı
    -0.19
    POSITIVE LOGITS
    ynes
    0.21
    ÐļÑĥпиÑĤÑĮ
    0.21
     INDIRECT
    0.20
    éĩı
    0.20
    ómo
    0.20
    /animations
    0.19
    .UserService
    0.19
    å¹Į
    0.19
    çĻ¾å¹´
    0.19
    enden
    0.19
    Activations Density 0.001%

    No Known Activations