© 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. 685
    Prev
    Next
    INDEX
    Explanations

    say Lith

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

    No Comments

    Negative Logits
    Austin
    -23.50
     Austin
    -23.38
     Texas
    -23.25
    Houston
    -22.63
    重庆
    -22.25
    重庆市
    -21.88
    (tx
    -21.63
    Texas
    -21.50
    (px
    -21.25
     Texans
    -21.13
    POSITIVE LOGITS
     Lith
    51.25
     Lithuania
    43.75
     lithium
    35.00
    锂
    33.00
     lith
    32.25
     лит
    28.00
     Armenian
    25.38
     LT
    25.38
     LI
    24.63
    LI
    24.13
    Activations Density 0.024%

    No Known Activations