© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14781
    Prev
    Next
    INDEX
    Explanations

    say Arctic

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Gal
    -17.38
     fert
    -17.13
    صيب
    -16.88
    ListView
    -16.13
     Binding
    -16.00
    绑定
    -15.81
    妾
    -15.69
    娃娃
    -15.50
     destiny
    -15.44
    hpp
    -15.38
    POSITIVE LOGITS
     Arctic
    25.63
     ice
    21.50
    冰
    21.13
    冰雪
    19.25
    Ice
    18.88
     Ice
    18.50
     Russians
    18.50
     Esk
    18.25
     Greenland
    18.13
    北极
    18.13
    Activations Density 0.199%

    No Known Activations