© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16348
    Prev
    Next
    INDEX
    Explanations

    say "5"

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

    No Comments

    Negative Logits
    tti
    -15.75
    procs
    -15.75
    巴巴
    -15.25
    клон
    -14.94
    cura
    -14.88
    rede
    -14.88
     bour
    -14.75
    otte
    -14.75
     sixteen
    -14.50
    ც
    -14.25
    POSITIVE LOGITS
    5
    52.50
     five
    50.00
     Five
    47.75
    五
    47.50
     fifth
    46.00
    five
    44.75
     Fifth
    44.00
    五个
    42.25
    Five
    40.75
     cinco
    40.50
    Activations Density 2.277%

    No Known Activations