© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 921
    Prev
    Next
    INDEX
    Explanations

    Journal name

    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
    /WebAPI
    -0.28
    /Dk
    -0.27
    abcdefghijkl
    -0.26
    ç»ıéªĮåĢ¼
    -0.24
    HeaderCode
    -0.24
    %!
    -0.24
    DMETHOD
    -0.24
    ----</
    -0.23
    ¡´
    -0.23
    -Identifier
    -0.23
    POSITIVE LOGITS
     Journal
    0.29
     J
    0.25
     journal
    0.24
     ar
    0.23
    Journal
    0.23
     journals
    0.22
    Curr
    0.22
    ç¾İ
    0.22
    J
    0.21
    berra
    0.21
    Activations Density 0.493%

    No Known Activations