© 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. 3297
    Prev
    Next
    INDEX
    Explanations

    say "question"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     sider
    -14.69
    array
    -14.50
     arrays
    -13.50
    組織
    -13.44
    组织
    -13.44
     Lun
    -13.31
    rene
    -13.13
    �
    -12.94
    Array
    -12.88
     массив
    -12.56
    POSITIVE LOGITS
     question
    54.00
    question
    47.50
     Question
    46.00
    Question
    44.25
    _question
    40.25
    .question
    39.25
    (question
    34.00
    -question
    33.25
     query
    33.00
    query
    31.75
    Activations Density 0.035%

    No Known Activations