© 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. 500
    Prev
    Next
    INDEX
    Explanations

    say directional words

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

    No Comments

    Negative Logits
     Bahrain
    -30.88
     Havana
    -30.75
     Singapore
    -30.25
    迪拜
    -30.25
     Honolulu
    -30.13
     Taipei
    -29.50
     Hait
    -29.38
    新加坡
    -28.88
     Egypt
    -28.63
     Dubai
    -28.63
    POSITIVE LOGITS
    汶
    18.13
     southwest
    18.00
     northwest
    17.25
    该县
    17.25
    涧
    16.63
    西南
    16.50
    山村
    16.25
     Southwest
    16.25
     southwestern
    15.75
    addle
    15.69
    Activations Density 0.265%

    No Known Activations