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

    Neuronpedia

    Jacobian LensNEW
    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. 975
    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
     Montana
    -22.50
    郯
    -22.25
    琅
    -21.13
    嵊
    -20.38
    剡
    -19.50
     Kansas
    -19.38
    沂
    -19.13
    (cs
    -17.75
     Franz
    -16.88
    临沂
    -16.88
    POSITIVE LOGITS
    在深圳
    74.00
    深圳
    70.50
    深圳市
    70.00
    宝安
    59.00
    圳
    42.00
    福田
    42.00
    惠州
    42.00
     Singapore
    41.50
    广东省
    40.50
    东莞
    40.25
    Activations Density 0.075%

    No Known Activations