© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16299
    Prev
    Next
    INDEX
    Explanations

    say "agent"

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

    No Comments

    Negative Logits
     shimmer
    -17.13
     HDF
    -16.75
    ceph
    -16.00
     CNC
    -15.25
    Firefox
    -14.81
    wordpress
    -14.81
     Alzheimer
    -14.81
     calorie
    -14.75
     Wordpress
    -14.69
    Apis
    -14.63
    POSITIVE LOGITS
    代理
    32.25
    代理人
    27.25
    代理商
    26.13
    经纪人
    25.75
    经纪
    25.25
     Agency
    24.75
     Agent
    24.63
    Agency
    24.13
    委托
    24.13
     agent
    24.00
    Activations Density 0.222%

    No Known Activations