© 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. 15812
    Prev
    Next
    INDEX
    Explanations

    say "evaluation metrics"}

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

    No Comments

    Negative Logits
     courseId
    -18.13
    brick
    -18.13
    SAMPLE
    -17.50
    CHILD
    -17.38
    Draft
    -17.13
    陵
    -16.88
    砖
    -16.88
     drafts
    -16.88
     CHILD
    -16.75
     draft
    -16.63
    POSITIVE LOGITS
    Accuracy
    23.50
     Accuracy
    23.00
     accuracy
    21.38
    _accuracy
    21.25
    accuracy
    20.63
     predictions
    20.38
     prediction
    18.75
     Precision
    18.63
     precision
    18.50
     accur
    18.25
    Activations Density 0.093%

    No Known Activations