© 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 4
    7. 3151
    Prev
    Next
    Layer 3Layer 5
    INDEX
    Explanations

    Ana in "Santa Ana"

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

    Ana/Anna in "Santa Ana"

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

    ak/el fragments after "An"

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

    the name "Santa Ana", firing most strongly on the final token "Ana" (and on "ANA" in all-caps) when it completes that place name.

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

    The final token of the name "Santa Ana" (or "Anna"), in any language, whether it's the city in California, the river, a church or hotel, or General Santa Anna. It fires on the "Ana/Anna/A" token right after "Santa".

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