© 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. 354
    Prev
    Next
    INDEX
    Explanations

    say non‑ASCII characters

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

    No Comments

    Negative Logits
    重庆
    -31.13
    重庆市
    -26.88
    渝
    -24.00
    聊城
    -23.50
     Venezuela
    -23.00
    顺德
    -23.00
    是韩国
    -22.50
    淄
    -21.88
     Venezuelan
    -21.50
    天津
    -21.25
    POSITIVE LOGITS
     �
    37.00
    闽
    23.75
    �
    23.25
     Celtic
    22.25
    ሻ
    22.00
    �
    21.88
    ሺ
    21.88
     NSString
    21.50
    畲
    21.38
    �
    21.38
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.