© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    say depth

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     variable
    -18.63
    变量
    -18.50
    variable
    -17.88
    _Variable
    -16.75
     перемен
    -16.63
    .variable
    -16.63
    党
    -15.94
    суд
    -15.88
    Variable
    -15.81
    _variable
    -15.75
    POSITIVE LOGITS
     depth
    47.25
    depth
    41.25
     Depth
    40.75
    深度
    40.50
    Depth
    39.25
    _depth
    33.75
    .depth
    33.50
    -depth
    31.13
    (depth
    30.88
     depths
    27.13
    Activations Density 0.061%

    No Known Activations