© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16127
    Prev
    Next
    INDEX
    Explanations

    say cooking

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

    No Comments

    Negative Logits
    链
    -17.75
    �
    -17.38
    鏈
    -17.25
    网站建设
    -16.88
    移动
    -16.88
    ADX
    -16.63
     glVertex
    -16.25
    长城
    -16.25
    Fixture
    -16.00
    �名
    -16.00
    POSITIVE LOGITS
     boiled
    22.25
    煮
    22.13
     cook
    22.13
     boiling
    21.25
     cooked
    20.75
    (raw
    19.88
     boil
    19.75
    焙
    19.50
    烘
    19.38
    加热
    19.38
    Activations Density 0.165%

    No Known Activations