© 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. 2090
    Prev
    Next
    INDEX
    Explanations

    say "certification"

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

    No Comments

    Negative Logits
    eping
    -18.50
    awning
    -18.50
    Ep
    -18.38
    ep
    -18.25
    _EP
    -18.13
     ep
    -18.13
    Mir
    -18.00
     Ep
    -17.50
    .protocol
    -16.88
    reflect
    -16.88
    POSITIVE LOGITS
    认
    42.25
    認
    34.50
     cert
    32.75
    认证
    32.25
    cert
    32.25
    Cert
    30.38
     Cert
    30.00
     certification
    30.00
    (cert
    29.38
     Certification
    28.25
    Activations Density 0.098%

    No Known Activations