© 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. 16086
    Prev
    Next
    INDEX
    Explanations

    [initial] => [surname]

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

    No Comments

    Negative Logits
    战士
    -17.25
     Voter
    -16.75
    烧
    -16.50
    发射
    -16.25
    EM
    -16.25
    adder
    -16.25
    emax
    -16.25
    leo
    -15.94
     EM
    -15.94
     painter
    -15.44
    POSITIVE LOGITS
    潮
    15.81
     ph
    15.56
    bac
    15.44
    .Car
    15.31
    玩笑
    15.06
     Php
    15.00
    蜓
    15.00
     Car
    15.00
    西洋
    15.00
    php
    14.88
    Activations Density 1.177%

    No Known Activations