© 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. 15599
    Prev
    Next
    INDEX
    Explanations

    say "exam" words

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

    No Comments

    Negative Logits
     Gerard
    -17.13
    分公司
    -16.88
    署
    -16.38
    锁定
    -16.25
     kickoff
    -16.13
    设计
    -16.13
     Kenn
    -16.00
     التع
    -15.94
    分校
    -15.88
    设计理念
    -15.88
    POSITIVE LOGITS
     examination
    23.13
     exam
    20.38
    exam
    19.88
     examinations
    19.38
     examined
    18.75
     Examination
    18.50
     Exam
    18.38
     examine
    18.38
    Exam
    16.75
     examining
    16.25
    Activations Density 0.073%

    No Known Activations