© 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. 861
    Prev
    Next
    INDEX
    Explanations

    say city names

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

    No Comments

    Negative Logits
    岳阳
    -30.25
    沅
    -29.00
     Sirius
    -23.88
    湘
    -23.63
    株洲
    -23.38
     Rh
    -22.75
    长沙
    -21.88
    长沙市
    -21.50
    九江
    -21.38
     rh
    -20.75
    POSITIVE LOGITS
    陇
    29.38
    绵阳
    27.25
    莆田
    27.13
     Cupertino
    26.50
     Urdu
    26.38
     Islamabad
    25.75
    义乌
    25.38
    甘肃
    24.88
    台州
    24.88
    宝鸡
    24.75
    Activations Density 0.457%

    No Known Activations