© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15961
    Prev
    Next
    INDEX
    Explanations

    say 珠

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

    No Comments

    Negative Logits
    IRO
    -26.25
    巡航
    -25.50
    桨
    -24.88
     Mosul
    -24.63
     curl
    -24.13
     Benghazi
    -23.13
    棹
    -23.00
    curl
    -22.88
    潘
    -22.88
    胰
    -22.75
    POSITIVE LOGITS
    珠
    31.50
     Monk
    25.00
    σ
    24.50
    sigma
    23.50
     Quincy
    23.25
    (sigma
    22.63
    雀
    22.38
    红豆
    22.25
     σ
    22.00
    珍珠
    21.88
    Activations Density 6.843%

    No Known Activations