© 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. 440
    Prev
    Next
    INDEX
    Explanations

    say "southern terms"

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

    No Comments

    Negative Logits
     Rolex
    -21.63
    伦敦
    -19.00
     Camel
    -18.75
    比利
    -18.50
     climbers
    -18.13
    珀
    -18.13
    沃尔沃
    -17.88
     Everest
    -17.88
     Welch
    -17.75
    奶粉
    -17.63
    POSITIVE LOGITS
     southern
    25.00
     Southern
    24.00
    南方
    23.38
    Southern
    23.13
     slave
    22.88
    south
    22.50
     south
    22.25
    /sl
    22.25
     South
    21.75
    South
    21.75
    Activations Density 0.208%

    No Known Activations