© 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. 468
    Prev
    Next
    INDEX
    Explanations

    say "rabbit"

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

    No Comments

    Negative Logits
    兖
    -20.50
    山东省
    -20.25
    德州
    -20.00
    峄
    -19.75
    济宁
    -19.63
    鄄
    -19.50
    济南市
    -19.38
     Carolina
    -19.38
    枣庄
    -19.13
    济南
    -19.00
    POSITIVE LOGITS
     rabbit
    56.75
    兔
    53.75
     rabbits
    52.00
    兔子
    50.75
     Rabbit
    50.75
    rabbit
    46.75
     Rab
    44.00
    .rabbit
    41.50
     bunny
    37.75
     Bunny
    37.00
    Activations Density 0.056%

    No Known Activations