© 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. 2673
    Prev
    Next
    INDEX
    Explanations

    民国

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

    No Comments

    Negative Logits
    	Vec
    -21.38
     Vec
    -20.88
    (Vec
    -20.50
    Vec
    -19.63
    <Vec
    -17.50
    .ser
    -17.25
     Fac
    -16.88
    利
    -16.38
    .Err
    -16.25
     refactor
    -16.13
    POSITIVE LOGITS
    民国
    24.38
     Milton
    21.00
     Benny
    20.38
     Institution
    18.25
    modify
    17.75
    MED
    17.00
     institution
    17.00
     modification
    16.88
     Modify
    16.88
     modifications
    16.38
    Activations Density 0.067%

    No Known Activations