© 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. 14025
    Prev
    Next
    INDEX
    Explanations

    say "explosion"

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

    No Comments

    Negative Logits
     processors
    -16.50
    调试
    -16.13
     brushes
    -15.88
     processing
    -15.81
    adders
    -15.75
     AppState
    -15.56
     BaseService
    -15.50
     Processor
    -15.50
    修改
    -15.38
    微信公众
    -15.31
    POSITIVE LOGITS
    爆炸
    30.50
     explosion
    29.00
     explosive
    28.25
    炸
    27.75
    冲击
    26.63
     explosions
    26.00
     exploding
    25.38
     blast
    25.13
     explode
    25.13
     Explos
    24.38
    Activations Density 0.463%

    No Known Activations