© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    say "机构"

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

    No Comments

    Negative Logits
     Sen
    -21.50
    Sen
    -20.50
     Demon
    -18.63
    Demon
    -18.13
     Sens
    -17.50
     Sentinel
    -16.88
     Demo
    -16.75
    .demo
    -15.94
     senator
    -15.88
     Pol
    -15.50
    POSITIVE LOGITS
    机构
    53.25
    機構
    40.75
     institution
    30.50
     Institutions
    27.63
     institutions
    27.38
     Institution
    25.38
     Str
    24.75
     str
    24.75
     strut
    23.88
     estr
    23.25
    Activations Density 0.065%

    No Known Activations