© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1201
    Prev
    Next
    INDEX
    Explanations

    dragon scales

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

    No Comments

    Negative Logits
    龙
    -30.25
    龍
    -24.38
     dragon
    -23.25
    Dragon
    -22.88
     Dragon
    -22.63
     snake
    -20.75
    黑龙
    -20.63
     Snake
    -19.63
    Snake
    -19.25
    dragon
    -18.75
    POSITIVE LOGITS
     circuit
    16.63
    afb
    16.50
    ParameterValue
    16.50
    电路
    16.25
    淀
    16.25
    PBS
    16.13
    的政治
    15.81
    党校
    15.69
    (factory
    15.69
    工厂
    15.63
    Activations Density 0.137%

    No Known Activations