© 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. 14009
    Prev
    Next
    INDEX
    Explanations

    say "martial arts"

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

    No Comments

    Negative Logits
    管理工作
    -18.75
    监听
    -18.00
    consume
    -17.50
    限购
    -17.50
    存款
    -17.25
    经营管理
    -17.13
    处理
    -17.00
     deposited
    -16.75
     deposit
    -16.38
     deposits
    -16.25
    POSITIVE LOGITS
    武术
    26.75
     training
    25.38
    训练
    24.88
    Training
    23.75
    拳
    23.13
    training
    22.75
     Training
    22.50
     Martial
    21.88
     martial
    21.25
    培训
    21.00
    Activations Density 0.197%

    No Known Activations