© 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. 14639
    Prev
    Next
    INDEX
    Explanations

    say distribution

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

    No Comments

    Negative Logits
    设计师
    -18.00
    执行
    -18.00
    应聘
    -17.50
    /exec
    -17.38
     execution
    -17.38
    设计
    -17.00
    _exe
    -17.00
    .design
    -16.63
     executing
    -16.63
     designer
    -16.25
    POSITIVE LOGITS
     Distribution
    24.88
     distribution
    23.50
    分布
    21.38
     distributions
    21.13
    distribution
    20.50
    _distribution
    19.38
    Distribution
    19.13
     DISTRIBUT
    18.00
     Distrib
    17.13
     distribute
    16.50
    Activations Density 0.089%

    No Known Activations