© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 859
    Prev
    Next
    INDEX
    Explanations

    say bone

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

    No Comments

    Negative Logits
     Mazda
    -23.38
    沔
    -18.50
     Costco
    -18.38
    苹果
    -17.88
     embroidered
    -17.50
     Jal
    -17.50
     Mexicans
    -17.38
    农机
    -17.25
     apple
    -16.75
     farmer
    -16.75
    POSITIVE LOGITS
    Bone
    25.25
    骨
    24.00
     bone
    24.00
    骨头
    23.88
     Bone
    23.13
    牙齿
    21.25
    化石
    20.88
     bones
    20.13
    bone
    19.50
    骨骼
    19.38
    Activations Density 0.084%

    No Known Activations