© 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. 15911
    Prev
    Next
    INDEX
    Explanations

    say water words

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

    No Comments

    Negative Logits
    屐
    -15.69
    括
    -15.69
    velte
    -15.56
    窗口
    -15.50
    牒
    -15.25
     jewish
    -15.25
     trúc
    -15.19
    Transpose
    -15.00
    引领
    -14.81
    porte
    -14.69
    POSITIVE LOGITS
    补水
    28.63
    供水
    26.63
    水泵
    25.25
     WATER
    24.88
     pump
    24.75
     watering
    24.63
     pumps
    24.00
    泵
    23.88
     Water
    23.50
     water
    23.38
    Activations Density 0.165%

    No Known Activations