© 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. 762
    Prev
    Next
    INDEX
    Explanations

    say Chinese locations

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

    No Comments

    Negative Logits
     Jama
    -24.00
    群岛
    -23.63
     Jamaica
    -23.25
    舟山
    -22.63
     lobster
    -21.00
    阿根廷
    -20.75
     Honolulu
    -19.88
    箬
    -19.88
     Auckland
    -19.88
     Hawai
    -19.88
    POSITIVE LOGITS
    晋
    27.00
    太原
    26.75
     von
    25.25
    石家庄
    24.50
    邺
    24.25
    山西省
    23.38
    河北省
    22.13
    保定
    22.13
    滏
    22.00
    魏
    21.88
    Activations Density 0.075%

    No Known Activations