© 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. 2050
    Prev
    Next
    INDEX
    Explanations

    say large numbers

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

    No Comments

    Negative Logits
     Mat
    -22.38
    Mat
    -20.38
     MAT
    -20.00
    .mat
    -19.50
    (Mat
    -19.38
     mat
    -19.00
     modulus
    -18.63
    mat
    -18.00
    Mir
    -17.50
    Mor
    -17.25
    POSITIVE LOGITS
    亿
    53.50
    Mill
    43.75
     billion
    43.50
     mill
    43.50
     million
    43.25
    億
    43.00
    千
    42.25
    million
    40.50
    mill
    40.25
     Mill
    39.75
    Activations Density 0.084%

    No Known Activations