© 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. 2505
    Prev
    Next
    INDEX
    Explanations

    senate

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

    No Comments

    Negative Logits
     hex
    -19.25
    hex
    -17.75
    [loc
    -17.25
    Der
    -17.25
    Hex
    -17.13
    Meg
    -16.88
    .der
    -16.88
     Hex
    -16.75
     config
    -16.75
    loc
    -16.75
    POSITIVE LOGITS
     senator
    39.25
     Senator
    39.00
     Sen
    38.50
    Sen
    38.00
     sen
    35.75
     Senate
    35.25
     senators
    35.00
    Senator
    35.00
    sen
    34.25
     Senators
    33.75
    Activations Density 0.060%

    No Known Activations