© 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. 3219
    Prev
    Next
    INDEX
    Explanations

    say stage

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Ster
    -18.88
     OG
    -18.00
     ster
    -17.88
    斯特
    -17.88
    ster
    -17.25
     Ster
    -17.00
     Sterling
    -16.75
    OG
    -15.88
    STER
    -15.44
    .St
    -15.25
    POSITIVE LOGITS
     stage
    83.50
     Stage
    75.00
    Stage
    74.00
    stage
    73.00
    	stage
    68.50
    阶段
    68.50
    (stage
    68.00
    _stage
    68.00
     stages
    64.50
    -stage
    63.25
    Activations Density 0.218%

    No Known Activations