© 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. 3327
    Prev
    Next
    INDEX
    Explanations

    template

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     tz
    -16.38
     Suites
    -16.13
    关系
    -15.94
     Tes
    -15.31
     tl
    -15.13
    tz
    -14.88
     trom
    -14.81
    (te
    -14.75
    _row
    -14.69
    芒
    -14.50
    POSITIVE LOGITS
     template
    53.25
    template
    49.00
    模板
    48.25
    	template
    46.75
     Template
    46.75
    Template
    46.25
    _template
    44.00
    -template
    43.50
    .template
    43.25
    (template
    43.25
    Activations Density 0.061%

    No Known Activations