© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2609
    Prev
    Next
    INDEX
    Explanations

    formal Chinese numerals

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

    No Comments

    Negative Logits
    ertext
    -15.44
     med
    -14.94
    .perform
    -14.88
    [loc
    -14.63
     pt
    -14.50
    在玩家
    -14.19
    pt
    -14.19
    isy
    -14.13
     simulated
    -13.94
    膨胀
    -13.81
    POSITIVE LOGITS
    壹
    55.25
     �
    45.50
    贰
    41.75
    叁
    41.75
    ¹
    40.00
    ³
    39.25
    乙方
    37.25
    �
    36.50
    ²
    36.50
    甲方
    34.50
    Activations Density 0.023%

    No Known Activations