© 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. 3762
    Prev
    Next
    INDEX
    Explanations

    programming syntax

    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
     HeaderComponent
    -0.24
    .Rollback
    -0.23
    è°©
    -0.22
     appré
    -0.20
    grese
    -0.20
    âĪİ
    -0.20
     withStyles
    -0.20
    /Grid
    -0.19
    UILDER
    -0.19
    _registro
    -0.19
    POSITIVE LOGITS
     scrut
    0.21
    :inline
    0.20
    æijģ
    0.20
     Ży
    0.19
    AttributeName
    0.19
    íĸīìłķ
    0.19
    ToUpper
    0.19
    (milliseconds
    0.18
    =\"$
    0.18
    <Pair
    0.18
    Activations Density 0.049%

    No Known Activations