© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 80
    Prev
    Next
    INDEX
    Explanations

    say astrophysics

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

    No Comments

    Negative Logits
     sugars
    -24.50
    糖
    -24.00
     sugar
    -23.38
    Sugar
    -22.88
     Sugar
    -22.38
    chlor
    -21.75
    (cache
    -21.13
    血糖
    -20.75
    盐
    -20.63
    Salt
    -20.50
    POSITIVE LOGITS
    发射
    18.63
    黑洞
    17.75
    Gamma
    17.25
    宇宙
    16.63
    引力
    16.50
     gamma
    16.13
     radiation
    16.13
     Radio
    16.13
     radio
    16.00
    天文
    15.88
    Activations Density 0.073%

    No Known Activations