© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2047
    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
     Microsoft
    -29.38
    微软
    -28.38
    Microsoft
    -28.13
     microsoft
    -27.13
    .azure
    -23.38
    Azure
    -23.13
    .microsoft
    -22.25
    azure
    -22.00
    icrosoft
    -21.75
     Azure
    -21.38
    POSITIVE LOGITS
     communication
    17.50
    沟通
    17.13
    口
    15.50
     communications
    15.44
    Communication
    15.06
     diarr
    14.81
    aling
    14.56
    通信
    14.19
     light
    14.00
    Communic
    13.94
    Activations Density 0.055%

    No Known Activations