© 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. 2311
    Prev
    Next
    INDEX
    Explanations

    say settlement

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

    No Comments

    Negative Logits
    digit
    -19.25
     digit
    -17.75
     mic
    -17.50
     DIG
    -17.38
     tmp
    -17.13
    antine
    -16.88
     erg
    -16.25
    ert
    -16.13
     cur
    -15.94
    徐
    -15.88
    POSITIVE LOGITS
     settlement
    59.25
     settlements
    53.50
     settle
    52.25
     Settlement
    50.50
     settled
    46.25
     settles
    44.25
     settling
    44.00
    结算
    40.50
     settlers
    38.25
    套
    35.75
    Activations Density 0.194%

    No Known Activations