© 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. 16260
    Prev
    Next
    INDEX
    Explanations

    say polarization

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

    No Comments

    Negative Logits
    坑
    -20.75
    _conn
    -18.88
     Conn
    -17.63
    送达
    -17.00
     Connection
    -17.00
    _connection
    -17.00
     CONNECTION
    -16.63
    Connection
    -16.63
    Connections
    -16.63
     connection
    -16.50
    POSITIVE LOGITS
     polar
    26.63
     polarization
    26.38
     Polar
    25.25
    偏
    19.63
     Stokes
    19.50
     Optical
    18.88
    光学
    18.75
     optical
    18.25
    旋转
    18.00
     rot
    17.75
    Activations Density 0.046%

    No Known Activations