© 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. 16236
    Prev
    Next
    INDEX
    Explanations

    say movement

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

    No Comments

    Negative Logits
     glove
    -18.25
     Brittany
    -18.13
    珙
    -17.38
     укра
    -17.13
    手套
    -17.00
     Sharon
    -17.00
     Dominican
    -16.63
     Cornel
    -16.63
    �
    -16.25
    .UUID
    -16.25
    POSITIVE LOGITS
    蹦
    23.13
     crawl
    22.25
    涧
    19.75
    舞
    19.38
     climb
    19.25
    牯
    19.13
    crawl
    18.88
    爬
    18.88
     crawling
    18.75
    涝
    18.75
    Activations Density 0.930%

    No Known Activations