© 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
    2. Qwen3-32B
    3. MLP Neurons - Layer 28
    4. 2169
    Prev
    Next
    Layer 27Layer 29
    INDEX
    Explanations

    Christmas

    np_max-act · claude-sonnet-5-5
    Triggered by @paultiplady

    Christmas and gifts

    np_max-act-logits · claude-sonnet-5-5
    Triggered by @paultiplady

    Chinese events and holidays

    np_min-act-logits · claude-sonnet-5-5Neg Acts
    Triggered by @paultiplady

    tokens in Christmas-themed text, especially holiday traditions and gift-giving, where the next word is likely to continue a festive or holiday-related phrase (e.g., "the" before gifts or lights, "it" before a Christmas-related verb).

    oai_token-act-pair · claude-sonnet-5-5
    Triggered by @paultiplady

    Words within personal blog-style texts about Christmas, such as function words (the, a, to) and holiday terms (Christmas, Santa, gift, unwrapping, presents) inside sentences about family traditions and holiday celebrations.

    eleuther_acts_top20 · claude-sonnet-5-5
    Triggered by @paultiplady
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Loading dashboard...