© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15813
    Prev
    Next
    INDEX
    Explanations

    say "billion"

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

    No Comments

    Negative Logits
     SCE
    -22.38
     Magnum
    -20.63
     Rogue
    -20.50
    SCR
    -20.50
     scape
    -19.75
    hung
    -19.63
     SAC
    -19.50
    チェ
    -19.13
    stakes
    -19.00
     Sabb
    -18.88
    POSITIVE LOGITS
     BILL
    27.13
    bill
    26.63
     bill
    26.50
    Bill
    26.50
     Bill
    25.13
    亿
    25.00
    BILL
    24.38
    _bill
    23.25
     billion
    22.63
    .bill
    21.75
    Activations Density 0.070%

    No Known Activations