© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1699
    Prev
    Next
    INDEX
    Explanations

    [宋] => [dynasties]

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

    No Comments

    Negative Logits
     Python
    -31.00
    Python
    -30.38
    宋代
    -29.75
     python
    -27.63
    宋
    -27.13
     PYTHON
    -26.63
    python
    -26.50
    PYTHON
    -26.50
    南宋
    -26.38
    _python
    -24.00
    POSITIVE LOGITS
     trades
    16.63
    蛋白
    15.69
     playerId
    15.69
    贸易
    15.38
    _pixel
    15.31
    羔
    15.31
    elsey
    15.25
    _player
    15.13
    球员
    14.94
    pixel
    14.81
    Activations Density 0.085%

    No Known Activations