© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1632
    Prev
    Next
    INDEX
    Explanations

    say "science"

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

    No Comments

    Negative Logits
     eggs
    -40.75
    鸡蛋
    -40.00
     egg
    -39.25
    蛋
    -38.75
     Egg
    -37.50
     Eggs
    -35.50
    egg
    -28.75
    卵
    -27.13
     emails
    -27.00
    Email
    -26.25
    POSITIVE LOGITS
    science
    21.50
    科学
    20.63
     Science
    19.75
     científ
    19.63
     science
    19.38
    과학
    18.75
     sciences
    18.38
    机动车
    18.25
    科學
    16.75
     scient
    16.50
    Activations Density 0.082%

    No Known Activations