© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1604
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    .ua
    -0.25
    imbus
    -0.22
    ¬ģ
    -0.22
    .nz
    -0.22
    /docker
    -0.21
    _endian
    -0.21
    /bower
    -0.21
    :mysql
    -0.20
    /jpeg
    -0.20
    _strdup
    -0.20
    POSITIVE LOGITS
    README
    0.28
    .html
    0.28
    .txt
    0.28
     UClass
    0.26
    .json
    0.25
     createState
    0.25
    .xml
    0.23
    /*.
    0.22
    {}.
    0.22
    .pdf
    0.22
    Activations Density 1.575%

    No Known Activations