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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 280
    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
    hti
    -22.13
    澧
    -20.88
    淇
    -20.13
    潢
    -20.13
    郏
    -19.63
    Va
    -18.63
     Tob
    -18.50
    嘉兴
    -17.88
    洺
    -17.63
     Becky
    -17.13
    POSITIVE LOGITS
    南京市
    60.25
    南京
    56.50
    金陵
    47.25
    广州市
    33.00
    在广州
    33.00
     df
    32.25
    广州
    32.00
    南宁
    31.88
    .df
    31.13
     Nan
    30.38
    Activations Density 0.050%

    No Known Activations