© 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. 305
    Prev
    Next
    INDEX
    Explanations

    say "Antarctic"

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

    No Comments

    Negative Logits
    灞
    -20.75
    梅州
    -19.25
     Syrians
    -19.13
    檬
    -19.13
    鄢
    -19.00
    税
    -18.88
    轵
    -18.75
    (cx
    -18.63
    栀
    -18.50
     Lebanese
    -18.38
    POSITIVE LOGITS
     Antarctic
    42.50
    南极
    41.25
     Antarctica
    41.25
    冰
    29.25
     ice
    28.75
     glacier
    28.00
    冰雪
    26.38
     polar
    26.13
     Ice
    25.75
     glaciers
    25.38
    Activations Density 0.126%

    No Known Activations