© 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. 14959
    Prev
    Next
    INDEX
    Explanations

    say "eight"

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

    No Comments

    Negative Logits
    旁
    -13.88
     juni
    -12.94
    和平
    -12.88
     Plate
    -12.88
     portfolios
    -12.44
    打得
    -12.44
     제
    -12.38
    側
    -12.25
    onders
    -12.06
    iola
    -11.94
    POSITIVE LOGITS
     eight
    41.75
    8
    41.00
     Eight
    40.75
    ８
    38.25
     eighty
    37.00
     eighth
    36.50
    eight
    36.50
    八个
    36.25
     Eighth
    36.25
    Eight
    36.00
    Activations Density 1.352%

    No Known Activations