© 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. 16096
    Prev
    Next
    INDEX
    Explanations

    moon

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

    No Comments

    Negative Logits
    茄子
    -23.75
    抢劫
    -22.63
    茄
    -22.50
     assassin
    -22.00
     Assassin
    -20.63
    椒
    -20.50
    鱿
    -20.38
    蓟
    -19.38
     createSelector
    -19.25
     Wrestling
    -19.00
    POSITIVE LOGITS
    (wx
    22.38
     Apollo
    22.00
    醴
    21.75
    磷
    20.75
    	wx
    20.75
    佛山
    20.38
     phosph
    20.25
     lunar
    20.00
    �
    19.88
     Lunar
    19.75
    Activations Density 5.518%

    No Known Activations