© 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. Qwen3-32B
    5. MLP Neurons - Layer 62
    7. 24399
    Prev
    Next
    Layer 61Layer 63
    INDEX
    Explanations

    maintain/maintenance

    np_max-act-logits · gemini-2.5-flash-lite
    Triggered by @paultiplady

    The marker token is used to highlight or extract specific words, phrases, or parts of words that might be of particular interest or significance in the context of the text, often including proper nouns, technical terms, or parts of compound words.

    eleuther_acts_top20 · gemini-2.5-flash-lite
    Triggered by @paultiplady

    maintain activity/sessions

    np_min-act-logits · gemini-2.5-flash-liteNeg Acts
    Triggered by @paultiplady

    specific information

    np_max-act · gemini-2.5-flash-lite
    Triggered by @paultiplady

    words related to government and education.

    oai_token-act-pair · gemini-2.5-flash-lite
    Triggered by @paultiplady
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Loading dashboard...