© 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. 2614
    Prev
    Next
    INDEX
    Explanations

    say "America" words

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

    No Comments

    Negative Logits
    mult
    -17.50
     protocol
    -16.25
     protocols
    -15.75
     ref
    -15.44
    -mult
    -15.38
     cert
    -15.38
     prot
    -15.00
    ugen
    -14.94
     institutions
    -14.81
    protocol
    -14.81
    POSITIVE LOGITS
     America
    30.75
    America
    29.00
     america
    22.88
    美洲
    22.63
     Amer
    22.00
    元
    20.88
    -Americ
    20.75
    美方
    20.75
    Dem
    19.88
     Anti
    19.75
    Activations Density 0.145%

    No Known Activations