© 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. 69
    Prev
    Next
    INDEX
    Explanations

    end

    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
    -strokes
    -0.37
     bureaucr
    -0.31
     libertine
    -0.30
     enthus
    -0.29
     sophistic
    -0.28
    pson
    -0.28
    geries
    -0.27
    -scenes
    -0.27
    -football
    -0.26
     Parenthood
    -0.26
    POSITIVE LOGITS
    /end
    0.29
    Hôtel
    0.25
    çļĦæľĢåIJİä¸Ģ
    0.24
    æĭľå¸ĪåѦèīº
    0.24
     end
    0.23
    [end
    0.23
    -end
    0.22
    æľĢåIJİä¸Ģ
    0.22
    (end
    0.22
     ends
    0.21
    Activations Density 2.638%

    No Known Activations