© 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. 2961
    Prev
    Next
    INDEX
    Explanations

    say parliament

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

    No Comments

    Negative Logits
    (cards
    -19.75
    (___
    -19.75
    (req
    -19.38
    glass
    -18.25
    _cards
    -18.13
    (sheet
    -17.88
    (card
    -17.88
    =req
    -17.38
    =device
    -17.13
     sheet
    -16.88
    POSITIVE LOGITS
    议会
    29.25
     parliament
    27.75
    Par
    27.13
     Parliament
    26.75
     par
    24.75
     Parl
    24.63
     Par
    23.25
     parl
    22.75
    -par
    22.13
    .par
    20.75
    Activations Density 0.078%

    No Known Activations