© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    Congress

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

    No Comments

    Negative Logits
    Congress
    -34.50
     Congress
    -33.75
     congressional
    -30.00
     congress
    -27.38
     Congressional
    -24.88
    国会
    -24.25
    直流
    -22.88
    	constructor
    -22.75
    神
    -22.38
    Construct
    -22.13
    POSITIVE LOGITS
    字
    21.75
     Alpine
    19.38
     字
    18.63
    武器
    15.69
    _AI
    15.19
    勇敢
    14.94
     Al
    14.81
    AI
    14.81
     AI
    14.69
    ��
    14.63
    Activations Density 0.045%

    No Known Activations