© 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 32
    7. 18369
    Prev
    Next
    Layer 31Layer 33
    INDEX
    Explanations

    left/link

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

    L'Hopital's rule

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

    Left

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

    mentions of the political party "Die Linke".

    oai_token-act-pair · gemini-2.5-flash-lite
    Triggered by @paultiplady

    Tokens indicating a political party ("Linke", "Link", "Venstre", "gauche"), directional terms ("left", "left", "left", "left", "left", "left", "left", "left", "left", "left"), or compound words starting with "left" ("-left").

    eleuther_acts_top20 · gemini-2.5-flash-lite
    Triggered by @paultiplady
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Loading dashboard...