© 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. 15855
    Prev
    Next
    INDEX
    Explanations

    [Isambard] => [Kingdom]

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

    No Comments

    Negative Logits
     spre
    -17.88
    稀
    -17.88
    softmax
    -17.63
    pread
    -17.50
     inflate
    -16.75
     vmax
    -16.63
    FLOW
    -16.63
    disp
    -16.50
     dispersed
    -16.50
    ष
    -16.38
    POSITIVE LOGITS
    城堡
    21.75
    鸭
    21.63
    悬挂
    21.50
    挂牌
    20.88
    掛
    19.88
     paras
    19.75
     Wings
    19.50
    duck
    19.13
     ducks
    18.63
    寨
    18.50
    Activations Density 0.478%

    No Known Activations