© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2309
    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
    ,arr
    -18.38
    arr
    -17.88
    _ARR
    -17.25
     arr
    -17.00
    icit
    -16.63
    	arr
    -15.88
    .arr
    -15.88
    (arr
    -15.81
     ARR
    -15.31
    蝙
    -15.31
    POSITIVE LOGITS
     certificate
    68.50
     Certificate
    65.50
    证书
    63.50
    Certificate
    63.25
     certificates
    62.25
     Cert
    62.00
     cert
    62.00
    cert
    59.75
    certificate
    58.25
    Certificates
    57.25
    Activations Density 0.070%

    No Known Activations