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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16098
    Prev
    Next
    INDEX
    Explanations

    say "water" words

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

    No Comments

    Negative Logits
    墩
    -24.75
    札
    -24.00
    坂
    -23.63
     Ridge
    -23.13
     Jade
    -23.00
    冈
    -22.63
     ridge
    -22.00
    笋
    -21.88
    三菱
    -21.75
     Bryant
    -21.50
    POSITIVE LOGITS
    游
    22.25
     aquatic
    22.00
    γ
    21.88
     flooding
    21.50
     Noah
    20.88
     floated
    20.50
     Flood
    20.38
    旅馆
    20.38
    饮水
    20.38
    鲸
    20.13
    Activations Density 7.515%

    No Known Activations