© 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. 310
    Prev
    Next
    INDEX
    Explanations

    say "San"

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

    No Comments

    Negative Logits
    MEA
    -18.63
     EG
    -17.88
    IAL
    -17.63
     MGM
    -17.50
     ME
    -16.63
     KL
    -16.50
    EG
    -16.38
    马来西亚
    -16.25
     Estonia
    -16.25
     Hazel
    -16.00
    POSITIVE LOGITS
     San
    71.00
    San
    65.50
     san
    55.75
    川
    55.00
     SAN
    53.50
     SF
    51.00
    SAN
    49.00
     Сан
    49.00
    san
    48.25
    _san
    47.75
    Activations Density 0.147%

    No Known Activations