© 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. 1129
    Prev
    Next
    INDEX
    Explanations

    say formula

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

    No Comments

    Negative Logits
     dance
    -50.75
    舞蹈
    -45.75
     dances
    -45.75
     Dance
    -45.50
    dance
    -43.25
     dancing
    -43.00
     danced
    -41.75
    舞
    -41.00
     dancers
    -38.75
     dancer
    -38.75
    POSITIVE LOGITS
     Formula
    19.00
    公式
    17.88
     formula
    17.88
    formula
    17.38
     formulas
    17.38
    -material
    17.13
    媒体
    16.75
    材质
    15.88
    apol
    15.81
     medi
    15.81
    Activations Density 0.061%

    No Known Activations