© 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. 4006
    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
     (;;
    -0.24
    ðŁļ©
    -0.24
    ")));
    -0.21
    Choices
    -0.21
    *)((
    -0.21
        	č↵
    -0.21
    /Dk
    -0.21
    üm
    -0.20
    "),"
    -0.20
    otime
    -0.20
    POSITIVE LOGITS
    ñana
    0.23
    (',',$
    0.22
    ide
    0.18
    dy
    0.18
    èĭ±æł¼
    0.18
    .UtcNow
    0.18
    layers
    0.18
     Coleman
    0.18
    æĻĤçĤ¹
    0.18
     sito
    0.17
    Activations Density 0.002%

    No Known Activations