© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14998
    Prev
    Next
    INDEX
    Explanations

    say "digits"

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

    No Comments

    Negative Logits
    kad
    -20.50
    вит
    -19.63
    roat
    -18.00
    usta
    -17.25
     Kro
    -17.25
    芭
    -17.25
     Kardashian
    -17.13
    usan
    -17.13
    pas
    -17.00
     Ballet
    -17.00
    POSITIVE LOGITS
    利物
    13.19
    ivery
    13.19
    colon
    13.13
    乖乖
    13.00
     moll
    13.00
    叼
    12.88
     Knife
    12.81
     mol
    12.63
     mockery
    12.63
     móc
    12.50
    Activations Density 0.014%

    No Known Activations