© 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. 3828
    Prev
    Next
    INDEX
    Explanations

    technical fragments

    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
    ampilkan
    -0.23
    ();)
    -0.20
    afür
    -0.20
     tooltips
    -0.20
    <Any
    -0.20
    (visitor
    -0.19
    uxtap
    -0.19
    è¾ľ
    -0.19
    retorno
    -0.19
     {*}
    -0.19
    POSITIVE LOGITS
    ÏĬ
    0.21
    iolet
    0.20
    iếu
    0.20
     ×Ķ×ķ×ĵ
    0.20
    WND
    0.20
    æĪİ
    0.19
    ç½
    0.19
    ulously
    0.19
    Directions
    0.19
     ApplicationController
    0.19
    Activations Density 0.001%

    No Known Activations