© 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. 2127
    Prev
    Next
    INDEX
    Explanations

    capital cities

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

    No Comments

    Negative Logits
     det
    -21.25
    (det
    -20.38
     mut
    -19.38
     er
    -18.75
     Mut
    -18.00
    .det
    -17.63
    Mut
    -17.38
    mut
    -17.38
     sim
    -16.88
    digit
    -16.75
    POSITIVE LOGITS
     Ottawa
    17.25
    OTT
    16.13
    Pot
    15.75
    议员
    15.38
     POT
    15.38
     Senators
    15.31
    otes
    14.94
     Protocol
    14.69
    _pot
    14.69
    inton
    14.56
    Activations Density 0.028%

    No Known Activations