© 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. 15950
    Prev
    Next
    INDEX
    Explanations

    say shoulder

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

    No Comments

    Negative Logits
     Candle
    -20.50
    烛
    -19.25
     Fuß
    -18.63
     Foot
    -17.88
     Kend
    -17.88
    趾
    -17.50
    裤
    -17.50
    双腿
    -17.38
    _foot
    -17.38
     candle
    -17.38
    POSITIVE LOGITS
    肩
    24.63
     shoulder
    23.50
     arm
    23.13
     Shoulder
    21.38
    肱
    20.88
    臂
    20.38
    _ARM
    20.38
    -arm
    20.00
     Arm
    19.75
     arms
    19.50
    Activations Density 0.100%

    No Known Activations