© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15374
    Prev
    Next
    INDEX
    Explanations

    say cake

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

    No Comments

    Negative Logits
    鞭
    -21.88
    肩
    -21.75
    臂
    -20.88
    方向盘
    -20.63
    scoped
    -19.88
    捩
    -19.38
    腕
    -18.63
    抖
    -18.63
    槍
    -18.50
    肱
    -18.38
    POSITIVE LOGITS
     Cake
    21.25
    杭
    21.00
    太湖
    20.00
    Cake
    19.88
     Everest
    19.38
    郅
    19.25
     cake
    19.25
     Krak
    19.00
     pq
    18.38
    cake
    18.00
    Activations Density 1.155%

    No Known Activations