© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15984
    Prev
    Next
    INDEX
    Explanations

    say "com"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    鳗
    -16.25
    蛋糕
    -15.44
    假冒
    -15.38
    赝
    -15.13
    伪造
    -14.50
     dairy
    -14.31
    worm
    -14.19
    Forgery
    -14.06
     кры
    -13.44
     tattoos
    -13.38
    POSITIVE LOGITS
     Com
    63.50
    Com
    63.25
    -com
    62.25
    com
    60.75
     COM
    60.25
     Kom
    59.75
    COM
    59.75
    	com
    59.25
    _com
    58.75
    (com
    58.75
    Activations Density 5.684%

    No Known Activations