© 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. 15165
    Prev
    Next
    INDEX
    Explanations

    digits

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

    No Comments

    Negative Logits
    背面
    -14.13
    łoż
    -13.88
    erah
    -13.81
    <small
    -13.81
    emain
    -12.94
    irection
    -12.75
    mare
    -12.69
    iates
    -12.69
    rowsing
    -12.56
    pressions
    -12.50
    POSITIVE LOGITS
    钜
    11.88
    打仗
    11.88
     Ма
    11.63
    阁
    11.56
    增添
    11.38
    aden
    11.25
    的根本
    11.19
    成效
    11.19
    .hardware
    11.13
    加油站
    10.81
    Activations Density 2.507%

    No Known Activations