© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 435
    Prev
    Next
    INDEX
    Explanations

    say Armenian

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

    No Comments

    Negative Logits
    湖州
    -22.50
    湛江
    -22.50
    惠州
    -21.13
    镇江
    -20.25
    箬
    -19.50
     Fairfield
    -19.38
    簰
    -19.38
     pineapple
    -19.25
     Connecticut
    -19.00
    Rotor
    -19.00
    POSITIVE LOGITS
     Armenian
    62.25
     Armenia
    57.00
     Armen
    54.75
     Azerbaijan
    36.00
     Azerbai
    34.75
     Kurdish
    31.13
     Assy
    30.25
     AR
    28.25
    Հ
    27.63
     Ар
    26.88
    Activations Density 0.059%

    No Known Activations