© 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. 454
    Prev
    Next
    INDEX
    Explanations

    say "place names"

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

    No Comments

    Negative Logits
    嘉兴
    -28.25
     Estonia
    -23.63
    瑞士
    -23.38
    浙江
    -22.75
     Tanzania
    -22.38
     Kerala
    -21.25
    浙江省
    -20.50
    印度
    -20.13
     Japan
    -20.00
     Bengal
    -20.00
    POSITIVE LOGITS
    西安市
    30.38
     Tehran
    29.50
    咸阳
    29.25
    郧
    26.00
    陕西省
    24.25
    �
    24.00
     Iranian
    23.75
    灞
    23.63
    浐
    23.38
     Fairfax
    23.00
    Activations Density 0.017%

    No Known Activations