© 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. 3776
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ÐļÑĥпиÑĤÑĮ
    -0.21
     xamarin
    -0.20
    è¾ļ
    -0.20
    ibrary
    -0.20
    .semantic
    -0.19
    noÅĽÄĩ
    -0.19
    æĴ¥
    -0.19
    arness
    -0.19
    :"-"`↵
    -0.19
    cordova
    -0.18
    POSITIVE LOGITS
    ecimal
    0.22
    uai
    0.21
    ziel
    0.21
    	Return
    0.20
    GBP
    0.19
    bbie
    0.18
    ofstream
    0.18
     Baba
    0.18
    bedo
    0.18
     Ä°stanbul
    0.18
    Activations Density 0.001%

    No Known Activations