© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4025
    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
    @↵↵
    -0.28
    .rar
    -0.26
     }}"><
    -0.26
    :;↵
    -0.25
    ,");↵
    -0.25
    ;br
    -0.24
    :request
    -0.23
    ,{"
    -0.22
    .Clamp
    -0.22
    GROUND
    -0.22
    POSITIVE LOGITS
     enthus
    0.23
     consect
    0.20
    è¿Ļ款车
    0.20
    è½²
    0.19
    æѤ
    0.19
     ningu
    0.19
    panse
    0.19
    ä»ķ
    0.19
    ảnh
    0.19
     ámb
    0.18
    Activations Density 0.000%

    No Known Activations