Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 162186
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
    icana
    -0.25
    飧
    -0.24
    æĸĩåĮĸåĴĮ
    -0.23
    peed
    -0.23
     dependency
    -0.23
    ingly
    -0.23
    ìĤ¬ìĿ´
    -0.22
    è§ĤæľĽ
    -0.22
     guiding
    -0.22
    å½ĵæĪij们
    -0.22
    POSITIVE LOGITS
    æľīå¾Īå¤ļç§į
    0.26
     stesso
    0.24
     likewise
    0.23
     fist
    0.23
     vice
    0.23
    广éĺĶ
    0.23
    /OR
    0.23
    åĽĽç§į
    0.23
    åIJĦå¼ıåIJĦæł·
    0.23
    å¤ļç§įå½¢å¼ı
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.