© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15759
    Prev
    Next
    INDEX
    Explanations

    say brand

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

    No Comments

    Negative Logits
     Sala
    -16.38
    ThreadPool
    -15.63
    肥
    -15.50
     Dudley
    -15.44
     Gore
    -15.44
     Chapel
    -15.38
    iddles
    -15.38
    чен
    -15.31
    Coder
    -15.31
     statist
    -15.25
    POSITIVE LOGITS
    的品牌
    44.50
    品牌
    43.00
     brand
    42.50
    品牌的
    40.25
    brand
    37.75
    Brand
    37.00
     brands
    36.75
     Brand
    36.50
    品牌形象
    36.25
     branding
    35.75
    Activations Density 0.219%

    No Known Activations