© 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. 2725
    Prev
    Next
    INDEX
    Explanations

    say "保"

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

    No Comments

    Negative Logits
     LAT
    -17.88
    DIG
    -17.13
    fac
    -16.88
     DIG
    -16.88
    reply
    -16.38
    Fac
    -15.56
    tent
    -15.38
    erca
    -15.13
     tents
    -14.75
    gé
    -14.75
    POSITIVE LOGITS
    保
    87.00
     preservation
    45.50
     conserv
    41.00
     Preservation
    40.75
     preserve
    39.75
    保留
    39.25
     preserves
    39.00
     conservation
    38.00
     preserving
    37.50
    preserve
    37.50
    Activations Density 0.084%

    No Known Activations