© 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. 15952
    Prev
    Next
    INDEX
    Explanations

    eating

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

    No Comments

    Negative Logits
     ZEND
    -19.38
    .temperature
    -17.75
    zend
    -17.50
     zend
    -17.38
    roid
    -17.38
     Zelda
    -17.25
     Cairo
    -17.25
    izona
    -17.13
    heatmap
    -17.00
    造价
    -17.00
    POSITIVE LOGITS
    吞
    31.75
     swallowing
    28.75
     swallow
    27.75
    吃
    27.00
    咀
    25.63
     swallowed
    25.25
     eating
    24.63
    胃口
    23.88
     ingestion
    23.75
     slur
    23.50
    Activations Density 0.179%

    No Known Activations