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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 466
    Prev
    Next
    INDEX
    Explanations

    say "ancient place names"

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

    No Comments

    Negative Logits
    纽约
    -21.13
     Hamburg
    -20.88
    瑞士
    -20.50
    挪威
    -20.25
     Swinger
    -20.00
     Norwegian
    -19.13
     Hof
    -18.88
     Lund
    -18.75
    浦东
    -18.63
    德国
    -18.38
    POSITIVE LOGITS
     Armenia
    22.75
     Maced
    22.63
     Assy
    22.38
     Armenian
    22.38
    秦
    21.38
    渑
    21.13
     Kurdish
    20.88
    秦国
    20.38
     Baghdad
    20.38
     Syria
    20.38
    Activations Density 0.119%

    No Known Activations