© 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. 321
    Prev
    Next
    INDEX
    Explanations

    Hindi‑English code‑switch

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

    No Comments

    Negative Logits
    郴
    -23.63
    粤
    -23.50
    广东
    -22.63
    江门
    -22.38
    威尼斯人
    -21.63
    广东省
    -21.38
    郴州
    -20.75
     Clement
    -20.38
     Singapore
    -20.25
    顺德
    -20.25
    POSITIVE LOGITS
     Colo
    18.75
    kaar
    18.63
     Loki
    18.50
     Icelandic
    18.00
     Boulder
    17.38
    碛
    17.25
    ഷ
    17.00
     Denver
    16.63
    ઉ
    16.63
    蓼
    16.13
    Activations Density 0.052%

    No Known Activations