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

    Neuronpedia

    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. 534
    Prev
    Next
    INDEX
    Explanations

    say "communication"

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

    No Comments

    Negative Logits
    龙泉
    -24.50
    ialog
    -21.13
     Kashmir
    -20.13
    京剧
    -19.75
     terrace
    -19.50
    茶园
    -19.13
     Caf
    -18.88
    olec
    -18.75
     singers
    -18.38
     Gotham
    -18.25
    POSITIVE LOGITS
    波特
    22.25
     baud
    20.00
    通信
    18.88
    发送
    18.13
    数据
    17.50
     PHY
    17.00
     bus
    16.88
     RTS
    16.75
     Packet
    16.75
     sending
    16.75
    Activations Density 0.079%

    No Known Activations