© 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. 478
    Prev
    Next
    INDEX
    Explanations

    say Arctic

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

    No Comments

    Negative Logits
    雒
    -25.00
    洛阳
    -24.38
     Naples
    -24.25
    柳州
    -24.00
    南宁市
    -23.00
    郑州市
    -21.88
     Toledo
    -21.63
    温州
    -21.50
     Bangalore
    -21.38
    郑州
    -21.13
    POSITIVE LOGITS
     Arctic
    44.25
     Alaska
    39.50
    冰
    36.75
    北极
    36.50
     Greenland
    36.00
     ice
    31.75
     Polar
    31.50
    冰雪
    30.88
     polar
    30.75
     thaw
    29.88
    Activations Density 0.380%

    No Known Activations