© 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. 3980
    Prev
    Next
    INDEX
    Explanations

    code or comments

    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
    :pointer
    -0.24
    ".↵↵↵↵
    -0.23
    aukee
    -0.23
     misog
    -0.22
    oriously
    -0.21
    ibile
    -0.21
    prus
    -0.21
    VisualStyle
    -0.21
    indre
    -0.20
    ournemouth
    -0.20
    POSITIVE LOGITS
    апÑĢимеÑĢ
    0.21
    ilmiÅŁ
    0.20
    没éĴ±
    0.20
    arsing
    0.20
    puties
    0.19
    å¾Ī满æĦı
    0.19
     trade
    0.19
    routeProvider
    0.18
    /////////////////////////////////////////////////////////////////////////////↵
    0.18
    绣çŃ¹æİ¨è¿Ľ
    0.18
    Activations Density 0.002%

    No Known Activations