© 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. 1191
    Prev
    Next
    INDEX
    Explanations

    [password] => [password]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     password
    -44.00
    密码
    -43.25
     Password
    -42.25
     passwords
    -41.25
    Password
    -40.00
    password
    -40.00
    -password
    -38.75
    	password
    -38.75
    .password
    -37.50
    _password
    -37.25
    POSITIVE LOGITS
     Illinois
    17.50
     Chicago
    17.25
     Lincoln
    17.00
     arts
    17.00
     chicago
    16.88
    芝加哥
    16.50
     arte
    16.25
     Booth
    16.13
    Chicago
    15.94
    ml
    15.81
    Activations Density 0.040%

    No Known Activations