© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15082
    Prev
    Next
    INDEX
    Explanations

    1 => 1

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onica
    -18.75
    ónica
    -17.88
    茚
    -16.38
    包袱
    -16.13
     candle
    -16.00
    キング
    -15.56
    onds
    -15.44
    봉
    -15.44
    ��
    -15.31
    ônica
    -15.31
    POSITIVE LOGITS
     sh
    17.88
    sh
    17.63
     thù
    16.00
    hardt
    15.94
    .arrow
    14.75
    พฤ
    14.63
     shutter
    14.50
     Sho
    14.38
    努
    14.38
    自由贸易
    14.25
    Activations Density 0.028%

    No Known Activations