© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    say "countries"

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

    No Comments

    Negative Logits
     Australia
    -38.25
    Australia
    -37.25
    澳大利亚
    -36.75
     Australian
    -31.63
    Australian
    -30.50
    澳洲
    -30.00
     Australians
    -28.63
    澳大
    -28.38
    审计
    -27.88
     australia
    -27.63
    POSITIVE LOGITS
     Tek
    16.88
     vect
    15.88
    技术
    15.38
     html
    15.31
    html
    15.31
     vectors
    15.19
    遗传
    15.00
    海军
    14.69
    Vectors
    14.44
     �
    14.38
    Activations Density 0.181%

    No Known Activations