© 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. 3180
    Prev
    Next
    INDEX
    Explanations

    box

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (mx
    -15.88
    ongyang
    -15.44
    manship
    -15.31
     yab
    -14.69
    [ix
    -14.56
     incarn
    -14.44
    筼
    -14.31
    istory
    -14.31
    (rx
    -14.25
    关系
    -14.13
    POSITIVE LOGITS
    箱
    73.50
     box
    68.00
    box
    61.50
     Box
    60.75
    Box
    57.75
    箱子
    56.50
    _box
    55.25
    	box
    55.25
    (box
    52.50
     boxes
    52.25
    Activations Density 0.045%

    No Known Activations