© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    [design] => [and]

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

    No Comments

    Negative Logits
    設
    -22.50
    设置
    -20.75
    设计
    -20.50
    设置了
    -18.75
     design
    -18.75
    設計
    -18.50
     Design
    -18.38
     Thiết
    -18.25
    设
    -17.63
    Design
    -17.50
    POSITIVE LOGITS
     spir
    16.38
    boom
    16.25
    orate
    16.00
    pir
    15.94
    phil
    15.75
    环绕
    15.31
     phantom
    15.25
     parameter
    15.25
    \Php
    14.81
    oids
    14.69
    Activations Density 0.145%

    No Known Activations