© 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. 2212
    Prev
    Next
    INDEX
    Explanations

    say 惠

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

    No Comments

    Negative Logits
     Termin
    -19.88
    Ter
    -18.75
     TERMIN
    -18.25
     Ter
    -18.00
    Leg
    -17.75
    _leg
    -17.63
    legs
    -16.50
     Reserved
    -16.38
    Reserved
    -16.00
     Legs
    -15.88
    POSITIVE LOGITS
    惠
    51.00
     ut
    28.25
     Hut
    26.00
    惠州
    25.88
     PT
    25.75
     pt
    24.13
    ut
    24.00
    UT
    23.13
    (pt
    22.63
     UT
    22.25
    Activations Density 0.023%

    No Known Activations