© 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. 19
    Prev
    Next
    INDEX
    Explanations

    say mary

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

    No Comments

    Negative Logits
    坂
    -21.88
     Karachi
    -21.25
    在深圳
    -20.88
    福田
    -20.88
    深圳市
    -20.75
     GST
    -20.63
    乌鲁木齐
    -20.25
    厝
    -19.88
    Australian
    -19.75
    台北
    -19.75
    POSITIVE LOGITS
     mary
    20.50
     Tud
    20.25
     Marian
    20.13
     Jaime
    20.00
     catholic
    19.75
    贞
    18.38
    玛丽
    18.25
     Mary
    18.13
    mary
    17.63
    Mary
    17.50
    Activations Density 0.166%

    No Known Activations