© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2697
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    TypeInfo
    -0.23
     CircularProgress
    -0.21
    letcher
    -0.20
    }><
    -0.20
    ieten
    -0.20
    гÑĢÑĥз
    -0.19
     doubly
    -0.19
     vidé
    -0.18
    linkplain
    -0.17
     poste
    -0.17
    POSITIVE LOGITS
    findViewById
    0.21
    ä¸ĸçķĮ第ä¸Ģ
    0.21
    æĹı
    0.20
    .spy
    0.20
    ãĢĸ
    0.20
    zych
    0.19
    conde
    0.19
     pictureBox
    0.19
    ä¸įåı¯æĢĿ
    0.19
    ç¥Ń
    0.19
    Activations Density 0.000%

    No Known Activations