© 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. 1468
    Prev
    Next
    INDEX
    Explanations

    parts of objects

    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
     Ivanka
    -0.24
    PropTypes
    -0.22
    -With
    -0.22
     cellFor
    -0.21
    ramento
    -0.21
     HeaderComponent
    -0.21
    rowsable
    -0.21
     propTypes
    -0.21
    ighton
    -0.21
    ospace
    -0.20
    POSITIVE LOGITS
    less
    0.28
    ä¸ĬçļĦ
    0.24
    å¾Īæ¼Ĥ亮
    0.23
     "-";↵
    0.22
    wró
    0.22
    -equipped
    0.21
    é¢ı
    0.21
    æĺ¯çĶ¨æĿ¥
    0.20
    ç»Ī身
    0.20
    .BorderSize
    0.19
    Activations Density 5.628%

    No Known Activations