© 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. 3304
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
     getDescription
    -0.21
    atin
    -0.20
    å°±ç»Ļ大家
    -0.20
     Randolph
    -0.20
    (strpos
    -0.19
    <stdlib
    -0.19
    REFERRED
    -0.19
    epar
    -0.18
     FontStyle
    -0.18
    orra
    -0.18
    POSITIVE LOGITS
    nyder
    0.21
     ../../../
    0.21
    aptors
    0.20
     crore
    0.20
    UIScrollView
    0.20
    ŀæĢ§
    0.20
    âĦĤ
    0.19
    .Interop
    0.19
    /***************************************************************************↵
    0.19
    olesale
    0.19
    Activations Density 0.002%

    No Known Activations