© 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. 14768
    Prev
    Next
    INDEX
    Explanations

    say 3

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

    No Comments

    Negative Logits
    3
    -42.00
    ３
    -36.25
     thirty
    -33.25
     Three
    -33.00
     three
    -32.50
    -three
    -32.00
     Thirty
    -31.50
    三百
    -31.25
    三十
    -30.75
    Thirty
    -29.13
    POSITIVE LOGITS
    八个
    21.38
    七个
    19.13
    五个
    19.00
    六个
    17.88
    四个
    16.75
    四位
    15.63
     fourteen
    15.44
    四项
    15.44
     four
    15.44
    四种
    15.00
    Activations Density 1.203%

    No Known Activations