© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    say "link"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    文件
    -19.75
    'field
    -18.25
    系统
    -17.88
    ��
    -17.25
    ACHI
    -17.00
     файла
    -16.75
    细胞
    -16.63
    ären
    -16.38
     Braun
    -16.25
    政府
    -16.25
    POSITIVE LOGITS
     link
    21.00
    道
    18.38
    Link
    18.38
    .tag
    17.38
     Links
    16.88
     tag
    16.88
    _link
    16.25
    _tag
    16.25
    TemplateName
    16.13
     Link
    15.81
    Activations Density 0.025%

    No Known Activations