© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 376
    Prev
    Next
    INDEX
    Explanations

    say "Los Angeles"

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

    No Comments

    Negative Logits
    鄂
    -29.63
     Estonia
    -25.13
     Eston
    -22.88
    邾
    -21.88
    蒙古
    -21.63
    鄱
    -21.25
    bcm
    -21.00
    襄阳
    -20.63
     Newfoundland
    -20.13
    箬
    -20.13
    POSITIVE LOGITS
     LA
    56.00
     Los
    50.50
    洛杉矶
    48.75
    LA
    48.00
    Los
    46.25
     UCLA
    39.75
    成都市
    36.50
    洛杉
    36.25
     LOS
    35.50
     LAP
    35.25
    Activations Density 0.131%

    No Known Activations