© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3050
    Prev
    Next
    INDEX
    Explanations

    designing and planning

    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
     komment
    -0.22
    swire
    -0.20
    ä½ĵèĤ²åľ¨çº¿
    -0.20
    éªĿ
    -0.20
    reements
    -0.19
    -Pack
    -0.19
     mitt
    -0.19
    owntown
    -0.19
     )))
    -0.19
    Passwords
    -0.19
    POSITIVE LOGITS
    enegro
    0.23
    åĮ»ç§ij
    0.20
     Coverage
    0.20
    ﹩
    0.19
     rall
    0.19
     ********************************************************************************
    0.19
    rysler
    0.19
    paren
    0.19
    èµĦ产éĩįç»Ħ
    0.19
     Erectile
    0.19
    Activations Density 0.004%

    No Known Activations