© 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. 3524
    Prev
    Next
    INDEX
    Explanations

    take

    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
    enaries
    -0.22
    ukan
    -0.21
     Magnum
    -0.20
    linky
    -0.20
    [DllImport
    -0.20
    enment
    -0.20
     <!--<
    -0.20
     Tos
    -0.19
    acija
    -0.19
    ãĥĭ
    -0.19
    POSITIVE LOGITS
    entiful
    0.25
     awhile
    0.24
    ä¹ĭåĬĽ
    0.22
     effort
    0.22
    },{↵
    0.20
     ÑĥÑģили
    0.20
     longer
    0.20
    him
    0.19
     RectTransform
    0.19
     place
    0.19
    Activations Density 0.075%

    No Known Activations