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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15453
    Prev
    Next
    INDEX
    Explanations

    say degree

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

    No Comments

    Negative Logits
    IRA
    -18.63
     insertion
    -17.88
    -cart
    -17.25
    enet
    -17.13
    价钱
    -16.88
    Cart
    -16.63
    orte
    -16.50
    socket
    -16.50
     Carp
    -16.50
    rone
    -16.00
    POSITIVE LOGITS
    学位
    27.13
    博士学位
    25.38
     degrees
    23.63
    _degree
    22.88
     degree
    22.38
    Deg
    21.75
    Degree
    21.75
     Degree
    21.13
     deg
    21.13
     PhD
    20.75
    Activations Density 0.110%

    No Known Activations