© 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. 14250
    Prev
    Next
    INDEX
    Explanations

    say statistics

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

    No Comments

    Negative Logits
    测试
    -18.25
    Test
    -17.13
     Tests
    -16.75
    TestClass
    -16.75
    @Test
    -16.75
     Test
    -16.75
     testName
    -16.63
     teste
    -16.50
     TEST
    -16.50
     testing
    -16.50
    POSITIVE LOGITS
    统计数据
    46.50
    统计
    45.00
     statistics
    43.25
    数据
    42.75
     statistic
    42.25
     data
    40.50
    的数据
    39.75
    数据分析
    38.75
     Statistics
    38.75
     stats
    38.75
    Activations Density 1.752%

    No Known Activations