© 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. 3920
    Prev
    Next
    INDEX
    Explanations

    same time

    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
    herits
    -0.23
    |array
    -0.22
    nqu
    -0.21
    sendMessage
    -0.20
    ="{!!
    -0.20
     sublic
    -0.19
    ,copy
    -0.19
    gency
    -0.19
    usted
    -0.19
     Oc
    -0.19
    POSITIVE LOGITS
    åIJĮä¸Ģ
    0.82
    åIJĮä¸Ģ个
    0.75
    åľ¨åIJĮä¸Ģ
    0.73
     same
    0.58
    same
    0.52
    _same
    0.50
     simultaneously
    0.49
    Same
    0.47
     Same
    0.47
    .same
    0.42
    Activations Density 0.817%

    No Known Activations