© 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. 2442
    Prev
    Next
    INDEX
    Explanations

    say "世"

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

    No Comments

    Negative Logits
    Pen
    -20.13
     sos
    -19.13
     Pen
    -18.63
     PEN
    -18.00
     penetration
    -16.38
    (hex
    -16.25
     pen
    -16.13
    _hex
    -16.00
    den
    -15.94
    pen
    -15.75
    POSITIVE LOGITS
    世
    50.00
     er
    27.00
     ter
    25.25
     Ter
    23.75
    ter
    23.38
    世人
    23.00
    Ter
    22.75
     Er
    21.75
    _ter
    20.25
     era
    20.13
    Activations Density 0.070%

    No Known Activations