© 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. 1969
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     vej
    -0.20
    æݧèĤ¡éĽĨåĽ¢
    -0.20
    :
    -0.20
     Families
    -0.19
    aux
    -0.19
     Hayward
    -0.19
     leve
    -0.19
    mod
    -0.19
    å·¥ä¸ļåĽŃåĮº
    -0.19
     Lanc
    -0.19
    POSITIVE LOGITS
    /Dk
    0.31
    )(*
    0.30
    #af
    0.30
    ",__
    0.30
    >tag
    0.29
    .MouseAdapter
    0.29
    __;
    0.29
    avanaugh
    0.29
    /↵↵↵↵
    0.28
    #aa
    0.28
    Activations Density 0.096%

    No Known Activations