© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1116
    Prev
    Next
    INDEX
    Explanations

    say country names

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

    No Comments

    Negative Logits
    Turkey
    -25.25
    土耳其
    -24.75
     Turkey
    -24.75
     Turkish
    -24.63
     Turks
    -23.25
     Ottoman
    -21.38
     تركيا
    -20.75
     Тур
    -20.50
     Ankara
    -19.25
    tur
    -19.13
    POSITIVE LOGITS
     mat
    17.25
     trade
    17.13
     law
    17.13
    mat
    16.88
     code
    16.50
    Google
    16.13
    tab
    15.44
    google
    15.19
     card
    15.06
     Google
    14.94
    Activations Density 0.135%

    No Known Activations