© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1423
    Prev
    Next
    INDEX
    Explanations

    say beans

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

    No Comments

    Negative Logits
    病毒
    -40.50
     viruses
    -40.50
     virus
    -38.75
     Virus
    -38.00
    病毒感染
    -37.75
     viral
    -36.75
     VIR
    -31.38
     Vir
    -31.25
    Vir
    -27.63
    VAS
    -25.63
    POSITIVE LOGITS
    佃
    14.56
    构建
    14.13
    西南
    14.06
    _sql
    13.94
    泵
    13.63
    uction
    13.50
     beans
    13.38
    豆
    13.13
    农业
    13.00
     Bean
    12.94
    Activations Density 0.109%

    No Known Activations