© 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. 3285
    Prev
    Next
    INDEX
    Explanations

    say selection

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    SV
    -18.75
    式
    -16.88
    体
    -16.25
    .ComponentModel
    -16.25
    _sv
    -15.94
     pathway
    -15.81
     chapter
    -15.69
    基地
    -15.63
    LEX
    -15.50
    encing
    -15.00
    POSITIVE LOGITS
     selection
    41.75
    selection
    41.25
    Selection
    37.75
     Selection
    37.00
    _selection
    34.25
    .selection
    34.00
    -selection
    31.50
     selections
    31.13
    (selection
    30.50
    _SELECTION
    29.25
    Activations Density 0.126%

    No Known Activations