© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14080
    Prev
    Next
    INDEX
    Explanations

    say learning

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

    No Comments

    Negative Logits
     broadcasts
    -18.50
    广播
    -18.38
    _devices
    -18.00
     broadcast
    -17.63
     filtering
    -17.00
    _Filter
    -16.88
    保卫
    -16.75
    播报
    -16.75
    设备
    -16.50
    炊
    -16.50
    POSITIVE LOGITS
    学习
    40.25
     learning
    37.25
    的学习
    36.50
    學習
    35.75
     Learning
    33.00
    Learning
    32.00
    learning
    31.63
    学习成绩
    31.13
    -learning
    30.63
     learn
    30.50
    Activations Density 0.745%

    No Known Activations