© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4215
    Prev
    Next
    INDEX
    Explanations

    unit tests

    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
    Negative Logits
    printStats
    -0.23
    åŀĥåľ¾æ¡¶
    -0.21
     rencont
    -0.21
    []=$
    -0.20
    issippi
    -0.20
    .="
    -0.19
    opportunitÃł
    -0.19
     withStyles
    -0.19
    lip
    -0.19
    IDGET
    -0.19
    POSITIVE LOGITS
    .junit
    0.24
    webdriver
    0.23
    /assert
    0.23
     tü
    0.23
    .selenium
    0.22
    ereotype
    0.21
    getMockBuilder
    0.21
    .epam
    0.21
    coverage
    0.21
    .testng
    0.20
    Activations Density 0.340%

    No Known Activations