© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16294
    Prev
    Next
    INDEX
    Explanations

    say "craft"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _visibility
    -16.75
    骅
    -16.63
    百合
    -16.63
     ADS
    -16.50
     Emirates
    -16.50
    emax
    -16.38
    欧元
    -16.38
     Zombies
    -16.38
    ós
    -16.25
    (candidate
    -16.25
    POSITIVE LOGITS
    匠
    22.63
    工匠
    20.88
    樵
    20.25
     trades
    19.25
    鞣
    18.88
     trade
    18.75
     craft
    17.88
     Crafts
    17.75
     Trades
    17.75
     craftsm
    17.63
    Activations Density 0.186%

    No Known Activations