© 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. 3679
    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
    #ad
    -0.22
    InputLabel
    -0.21
    è·ª
    -0.20
    eree
    -0.20
    IsRequired
    -0.19
     Beverly
    -0.19
     CircularProgress
    -0.18
    æīª
    -0.18
    dden
    -0.17
    <fieldset
    -0.17
    POSITIVE LOGITS
    forcements
    0.23
     rencont
    0.22
    cratch
    0.20
     bloginfo
    0.20
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.19
     Tem
    0.19
    dbh
    0.18
    ä¸İä¼Ĺ
    0.18
    -aos
    0.18
     полÑĮзÑĥ
    0.18
    Activations Density 0.001%

    No Known Activations