© 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. 15674
    Prev
    Next
    INDEX
    Explanations

    say "8"

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

    No Comments

    Negative Logits
    制药
    -14.94
     Miranda
    -14.81
    爵士
    -14.50
    anje
    -14.06
    苒
    -13.81
     Plymouth
    -13.75
     antibiot
    -13.56
     bru
    -13.31
    ling
    -13.25
     trọng
    -13.25
    POSITIVE LOGITS
    8
    50.50
    八
    48.50
     eight
    48.00
    ８
    42.50
     eighty
    42.25
    八个
    42.00
     Eight
    42.00
     eighth
    41.25
    eight
    40.00
    -eight
    38.25
    Activations Density 2.487%

    No Known Activations