© 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. 278
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    秦皇岛
    -31.63
    鲅
    -30.75
     Tamil
    -29.25
    瓯
    -26.88
    鲛
    -26.75
    辽宁省
    -25.88
    大海
    -25.88
    威海
    -25.75
     Wilmington
    -25.25
    鞍山
    -25.25
    POSITIVE LOGITS
    菊花
    22.25
    菊
    21.25
    莴
    21.13
     Bronx
    20.75
     timeZone
    20.25
     MGM
    20.13
    .hu
    20.00
    硚
    19.88
    茼
    19.38
     Mozart
    19.25
    Activations Density 0.461%

    No Known Activations