© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16280
    Prev
    Next
    INDEX
    Explanations

    say bag

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

    No Comments

    Negative Logits
    .createUser
    -20.88
     createUser
    -19.25
     CreateUser
    -19.13
    phis
    -18.75
     oauth
    -18.63
    炙
    -18.50
    产销
    -17.75
    生产企业
    -17.50
    ystem
    -17.00
    rome
    -16.88
    POSITIVE LOGITS
    袋子
    24.00
    袋
    23.88
     bag
    23.50
     bags
    22.50
     purse
    20.63
    Bag
    20.25
    bag
    20.25
    垃圾桶
    20.00
     trash
    19.88
    垃圾
    19.88
    Activations Density 0.324%

    No Known Activations