© 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. 2596
    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
    磻
    -0.24
    благо
    -0.24
    .Globalization
    -0.23
    udiantes
    -0.23
    /WebAPI
    -0.22
    :numel
    -0.21
     createState
    -0.21
    {_
    -0.20
    åıĪ好åıĪ
    -0.20
    cação
    -0.20
    POSITIVE LOGITS
    iore
    0.20
    LineStyle
    0.20
    quo
    0.18
    stderr
    0.18
    leet
    0.18
    upy
    0.18
    ushman
    0.18
    kee
    0.17
    [strlen
    0.17
    æŃ¤é¡¹
    0.17
    Activations Density 0.001%

    No Known Activations