© 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. 15801
    Prev
    Next
    INDEX
    Explanations

    say "certificate"

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

    No Comments

    Negative Logits
    营养
    -19.88
    羽毛球
    -19.13
    减肥
    -18.13
    .inflate
    -17.88
     STATS
    -17.75
    weather
    -17.75
    分彩
    -17.75
    粜
    -17.75
    dropdown
    -17.63
    icolor
    -17.63
    POSITIVE LOGITS
    证书
    37.75
     certificate
    37.25
     Certificate
    35.25
     cert
    34.50
     certificates
    34.00
     Cert
    32.25
    Certificate
    32.00
    certificate
    30.50
    Cert
    29.75
     certs
    29.75
    Activations Density 0.141%

    No Known Activations