© 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. 3076
    Prev
    Next
    INDEX
    Explanations

    say "line"

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

    No Comments

    Negative Logits
    ules
    -16.88
    ATIONAL
    -14.44
    阁
    -14.19
    igel
    -14.19
    plash
    -14.06
    andal
    -14.00
    IGATION
    -13.69
    羝
    -13.50
    传出
    -13.50
    itates
    -13.50
    POSITIVE LOGITS
     line
    107.50
     Line
    98.50
    Line
    94.00
    line
    91.50
    _line
    89.50
    .line
    85.00
    -line
    84.00
    	line
    83.00
     lines
    81.00
    =line
    79.00
    Activations Density 0.361%

    No Known Activations