© 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. 3073
    Prev
    Next
    INDEX
    Explanations

    specific items

    np_max-act-logits · gemini-2.5-flash-lite
    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
     UsersController
    -0.23
     seedu
    -0.22
     potrÃł
    -0.22
    à¥IJ
    -0.20
    صÙĨد
    -0.20
    âĹĤ
    -0.20
     SetLastError
    -0.19
     messageType
    -0.19
    .cid
    -0.19
    CCCCCC
    -0.19
    POSITIVE LOGITS
    .Collectors
    0.26
    %"><
    0.22
    iffany
    0.20
    éī´å®ļ
    0.20
    здание
    0.19
    antro
    0.18
    mouseout
    0.18
    ,},↵
    0.18
    åIJİéĿ¢çļĦ
    0.18
    reu
    0.18
    Activations Density 0.004%

    No Known Activations