© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14311
    Prev
    Next
    INDEX
    Explanations

    say dance

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

    No Comments

    Negative Logits
     Pdf
    -17.63
    dens
    -17.38
    信誉
    -16.13
    >window
    -15.88
     outputFile
    -15.81
    PDF
    -15.81
     autos
    -15.44
     Presidency
    -15.38
    (volume
    -15.38
    olson
    -15.38
    POSITIVE LOGITS
    舞
    48.75
    舞蹈
    47.25
     dance
    46.00
     danced
    43.50
     Dance
    43.25
    跳舞
    43.00
     dances
    42.25
     dancers
    41.50
     dancing
    41.00
     dancer
    40.50
    Activations Density 0.235%

    No Known Activations