© 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. 1024
    Prev
    Next
    INDEX
    Explanations

    math and code

    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
     ${({
    -0.22
     Incontri
    -0.21
    èĪ¸
    -0.21
    bbie
    -0.20
     preco
    -0.20
     handguns
    -0.20
    å¿ĥ仪
    -0.19
     semiclass
    -0.19
    -bed
    -0.19
     roma
    -0.19
    POSITIVE LOGITS
    ãİŀ
    0.28
    ()=="
    0.22
    кÑĤив
    0.22
    ernals
    0.22
    seo
    0.21
    uters
    0.21
    ossal
    0.21
    ="__
    0.21
    fällt
    0.20
    .ExecuteReader
    0.20
    Activations Density 0.087%

    No Known Activations