© 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. 3763
    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
    æģ¯
    -0.25
    -Trump
    -0.25
     giochi
    -0.24
    structuring
    -0.22
    trys
    -0.21
     ?>"/>↵
    -0.21
     sodom
    -0.21
     ++)↵
    -0.21
     addCriterion
    -0.20
    engkap
    -0.20
    POSITIVE LOGITS
    çĬĴ
    0.22
    .SelectedIndexChanged
    0.22
    ï¼ļ%
    0.21
    [sizeof
    0.20
    åIJ«æľī
    0.20
    _requires
    0.19
    <decltype
    0.19
    éķĿ
    0.18
    âīĮ
    0.18
    åķŃ
    0.18
    Activations Density 0.000%

    No Known Activations