© 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. 3300
    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
    æĪĺ士æĿ¥è¯´
    -0.25
    ;!
    -0.25
    /Dk
    -0.24
    rette
    -0.23
    ’B
    -0.21
    [".
    -0.21
    swick
    -0.21
    retweeted
    -0.21
    į°ìĿ´
    -0.20
    oubted
    -0.20
    POSITIVE LOGITS
    /*↵
    0.22
     estratégia
    0.20
    iping
    0.20
     fronts
    0.20
    _angles
    0.19
     atol
    0.19
    åIJĮæĦı
    0.18
     puls
    0.18
    VectorXd
    0.18
    gorm
    0.17
    Activations Density 0.001%

    No Known Activations