© 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. 16193
    Prev
    Next
    INDEX
    Explanations

    say "angel"

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

    No Comments

    Negative Logits
    綠
    -18.50
    豆腐
    -18.38
     Rug
    -17.38
    农副产品
    -17.13
    木地板
    -17.00
    中国经济
    -16.88
    green
    -16.88
    Green
    -16.88
    HashMap
    -16.75
     patches
    -16.75
    POSITIVE LOGITS
    天使
    24.13
     angel
    22.88
    angel
    22.13
     Angels
    22.13
     Angel
    20.88
     angels
    20.25
     Angelo
    19.75
     Ange
    18.63
    霄
    18.50
    Angel
    18.25
    Activations Density 0.132%

    No Known Activations