© 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. 3104
    Prev
    Next
    INDEX
    Explanations

    level

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    lke
    -17.50
     Sterling
    -17.25
    eling
    -16.75
    isko
    -16.25
     alb
    -15.44
     Thomas
    -15.25
    uable
    -15.19
    це
    -15.06
    connection
    -14.56
    Thomas
    -14.56
    POSITIVE LOGITS
     level
    86.50
    level
    80.00
     Level
    78.00
    Level
    76.50
    _level
    76.00
    (level
    72.50
    .level
    70.00
    	level
    70.00
     levels
    67.00
    水平
    66.00
    Activations Density 0.292%

    No Known Activations