© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3189
    Prev
    Next
    INDEX
    Explanations

    say "distribution"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    方法
    -15.88
    这种方法
    -15.75
    债
    -15.50
     method
    -14.88
    HeaderCode
    -14.63
     MODULE
    -14.50
    MODULE
    -14.25
    词
    -14.25
    method
    -14.06
    ropol
    -14.06
    POSITIVE LOGITS
     distribution
    60.00
    distribution
    57.50
     Distribution
    54.25
    Distribution
    52.75
    分布
    51.00
    _distribution
    48.50
     distributions
    43.75
    istribution
    36.75
     DISTRIBUT
    35.00
     distribute
    34.25
    Activations Density 0.100%

    No Known Activations