© 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. 2703
    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
    otland
    -0.27
    [".
    -0.26
    :view
    -0.25
    >{"
    -0.25
    ',//
    -0.24
    =-=-
    -0.24
    anye
    -0.24
    ;!
    -0.24
    odka
    -0.24
    ;',↵
    -0.23
    POSITIVE LOGITS
    signature
    0.21
    åı¯ä»¥æĽ´å¥½
    0.19
    AUTO
    0.19
    éĢīæĭ
    0.19
    akov
    0.19
    åıįèħIJåĢ¡å»ī
    0.19
    åįĬ导
    0.18
    ãĤĵãģª
    0.18
     beneficiation
    0.18
     août
    0.18
    Activations Density 0.000%

    No Known Activations