© 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. 2020
    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
    ï¿¡
    -0.20
    念
    -0.20
    åIJ¸
    -0.19
    orno
    -0.19
    emetery
    -0.19
    ",__
    -0.19
     Nack
    -0.19
    .itemView
    -0.19
     vmax
    -0.18
    ideon
    -0.18
    POSITIVE LOGITS
     Barang
    0.23
     (!((
    0.23
    bsolute
    0.23
    uxtap
    0.22
    ëĥ¥
    0.21
    广åijĬæľįåĬ¡
    0.21
    æĸ°éĹ»åıijå¸ĥ
    0.21
    媸
    0.20
    ç½ij绾ç§ijæĬĢ
    0.19
    anship
    0.19
    Activations Density 0.001%

    No Known Activations