© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14093
    Prev
    Next
    INDEX
    Explanations

    citations

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

    No Comments

    Negative Logits
     group
    -17.50
    GroupName
    -17.13
    组
    -17.13
    (group
    -17.00
    团
    -16.38
    滤
    -16.25
    组件
    -16.25
    解答
    -16.25
    otope
    -16.13
    数学
    -16.00
    POSITIVE LOGITS
     sources
    24.38
    source
    23.38
     quoting
    22.75
     quotation
    22.63
     quote
    22.63
     source
    22.50
    Source
    21.75
     Source
    21.50
     Sources
    21.38
    sources
    21.00
    Activations Density 0.546%

    No Known Activations