© 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. 1354
    Prev
    Next
    INDEX
    Explanations

    with

    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
     partager
    -0.23
    ãĤĤãģ¡ãĤį
    -0.22
     XCTAssertTrue
    -0.21
     gamm
    -0.21
    -strokes
    -0.21
     choisir
    -0.20
    aukee
    -0.20
    è¡Įãģı
    -0.20
    ä¼Ĺ
    -0.20
    ÑģÑĤолÑĮ
    -0.19
    POSITIVE LOGITS
    standing
    0.47
     regards
    0.47
     regard
    0.45
    stood
    0.41
    drawing
    0.35
    outh
    0.32
    olding
    0.32
     respect
    0.32
    holds
    0.30
    holding
    0.29
    Activations Density 1.404%

    No Known Activations