© 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. 16074
    Prev
    Next
    INDEX
    Explanations

    say named entities

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

    No Comments

    Negative Logits
    捶
    -28.38
     Glock
    -24.13
    撞击
    -24.00
     Bang
    -23.50
    槌
    -23.00
    捣
    -22.38
     Hammer
    -22.38
     Nail
    -21.88
    爆
    -21.88
     Storm
    -21.75
    POSITIVE LOGITS
     Shib
    23.88
     Shir
    22.13
    仙
    20.00
    希腊
    20.00
    _PY
    19.50
    政协
    19.38
     Python
    19.25
    茭
    19.00
    _RC
    19.00
    乐视
    18.88
    Activations Density 6.806%

    No Known Activations