© 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. 2062
    Prev
    Next
    INDEX
    Explanations

    say "ger"

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

    No Comments

    Negative Logits
    万
    -18.13
    萬
    -17.63
    Mirror
    -17.13
    strip
    -17.13
     Mutual
    -16.75
     nghìn
    -16.50
    魔
    -16.50
    (strip
    -16.38
     Thousand
    -16.38
    dims
    -16.25
    POSITIVE LOGITS
     Ger
    67.50
     ger
    67.50
    Ger
    65.00
     GER
    54.25
    ger
    54.00
    GER
    48.00
     germ
    47.75
     mer
    42.50
     Germ
    39.00
    mer
    38.00
    Activations Density 0.114%

    No Known Activations