© 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. 606
    Prev
    Next
    INDEX
    Explanations

    say Morocco

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

    No Comments

    Negative Logits
    福建省
    -21.50
     Киев
    -20.75
     Taiwan
    -20.75
     Romanian
    -20.50
     Vader
    -20.00
    兖
    -19.50
     Illinois
    -19.13
    是韩国
    -18.75
     Indianapolis
    -18.75
    .ts
    -18.75
    POSITIVE LOGITS
     Morocco
    49.50
     Moroccan
    45.00
    银川
    34.00
    宁夏
    32.75
     Marr
    31.88
    Mor
    31.63
     المغرب
    28.25
     Maurit
    28.13
     Algeria
    27.38
    仫
    27.38
    Activations Density 0.062%

    No Known Activations