© 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. 2071
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
     ?>"/>↵
    -0.23
    åľ¨è¿ĩæ¸¡æľŁ
    -0.22
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.21
    xFFFFFF
    -0.20
    建档ç«ĭ
    -0.20
    é¾Į
    -0.20
    :CGRect
    -0.20
    æ¡«
    -0.20
    (iOS
    -0.19
    ï¼ĥ
    -0.19
    POSITIVE LOGITS
    pecia
    0.21
    isbury
    0.20
    agnar
    0.20
    :maj
    0.20
    ungeons
    0.20
     Atatürk
    0.19
    <decltype
    0.19
    yectos
    0.19
     generado
    0.19
    кл
    0.19
    Activations Density 0.001%

    No Known Activations