© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15918
    Prev
    Next
    INDEX
    Explanations

    say supervision

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

    No Comments

    Negative Logits
    NSBundle
    -17.25
     Appalach
    -16.63
     Mét
    -15.63
    肤色
    -15.44
    .header
    -15.31
    .hl
    -15.00
    accum
    -14.81
    采摘
    -14.56
    棕色
    -14.50
    andle
    -14.38
    POSITIVE LOGITS
    监督
    51.50
     supervision
    43.75
    监视
    43.50
    监控
    41.50
    監
    40.25
     Superv
    39.75
     monitoring
    39.00
     superv
    38.50
    监督管理
    38.50
    监督检查
    37.50
    Activations Density 0.223%

    No Known Activations