© 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. 15539
    Prev
    Next
    INDEX
    Explanations

    say million

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

    No Comments

    Negative Logits
     tq
    -21.38
     Gus
    -20.38
     GTX
    -20.38
    底盘
    -20.00
    ETER
    -19.88
    psc
    -19.75
     Thur
    -19.63
     gamb
    -19.25
    pak
    -19.25
     Parker
    -19.25
    POSITIVE LOGITS
    million
    21.63
    百万
    21.50
     مليون
    21.38
     millones
    20.13
     million
    20.13
     millions
    19.25
    Mill
    18.75
     Mario
    18.63
     Million
    18.50
    lion
    18.50
    Activations Density 0.109%

    No Known Activations