© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 287
    Prev
    Next
    INDEX
    Explanations

    ducks and geese

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

    No Comments

    Negative Logits
    阿根廷
    -20.63
    斐
    -20.00
     Rafael
    -19.88
    成都市
    -18.75
    攀
    -18.25
    矿山
    -17.63
     li
    -17.13
    忉
    -17.00
     Santiago
    -16.88
    巴西
    -16.63
    POSITIVE LOGITS
    鸭
    36.75
     duck
    34.00
     Ducks
    32.50
     ducks
    31.75
     Goose
    30.75
     Duck
    30.25
    duck
    30.00
     goose
    29.50
    藕
    25.38
     Dutch
    24.50
    Activations Density 0.098%

    No Known Activations