© 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 51
    7. 17360
    Prev
    Next
    Layer 50Layer 52
    INDEX
    Explanations

    multilingual

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

    The token "that" is used in various grammatical constructions, including as a conjunction, demonstrative pronoun, and relative pronoun, often following prepositions or verbs, and preceding clauses or phrases that provide additional information, explanation, or condition.

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

    former or latter

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

    The texts are in multiple languages and cover a wide range of topics, making it impossible to identify a broad theme or context. First token in MAX_ACTIVATING_TOKENS: dass

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

    phrases involving commands or instructions.

    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...