© 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. 1457
    Prev
    Next
    INDEX
    Explanations

    social

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

    No Comments

    Negative Logits
    Social
    -53.00
     social
    -51.25
    社会
    -51.00
     Social
    -51.00
    social
    -49.75
    社會
    -46.50
    和社会
    -46.00
    -social
    -45.00
    的社会
    -44.75
    _social
    -42.25
    POSITIVE LOGITS
    像素
    13.94
     Bird
    13.75
    鹭
    13.69
     Brexit
    13.63
     Pixels
    13.44
    ICLE
    13.13
     pedal
    13.06
     Pixel
    13.00
     pixel
    13.00
    (lambda
    12.81
    Activations Density 0.363%

    No Known Activations