© 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. 15626
    Prev
    Next
    INDEX
    Explanations

    say parliamentary terms

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

    No Comments

    Negative Logits
    投资项目
    -18.63
    个项目
    -17.38
    熊猫
    -16.50
     scoreboard
    -16.25
     frosting
    -15.88
     projects
    -15.81
     scoring
    -15.69
    'label
    -15.63
     project
    -15.50
    .kafka
    -15.31
    POSITIVE LOGITS
     Parliament
    27.38
    议会
    25.50
     legislators
    25.38
     parliament
    25.25
     legislature
    25.13
    立法
    25.00
     legislative
    24.88
    semblies
    24.75
     Assembly
    24.50
    议员
    24.50
    Activations Density 0.140%

    No Known Activations