© 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. 15371
    Prev
    Next
    INDEX
    Explanations

    say domains

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

    No Comments

    Negative Logits
    filme
    -19.00
    舜
    -17.63
    模特
    -17.50
    壁画
    -17.38
    tile
    -17.25
    thetic
    -17.13
    银河
    -16.75
    卡片
    -16.63
    arton
    -16.50
    壁纸
    -16.50
    POSITIVE LOGITS
     domains
    29.75
     domain
    28.63
    DNS
    27.75
    Domains
    27.50
    Domain
    27.38
    domains
    27.00
    域名
    26.88
    DOMAIN
    26.25
     Domain
    26.13
    dns
    26.13
    Activations Density 0.117%

    No Known Activations