© 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. 3030
    Prev
    Next
    INDEX
    Explanations

    Lego

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

    No Comments

    Negative Logits
     et
    -19.75
     ET
    -18.38
    _ET
    -18.00
     CAP
    -17.63
     TEM
    -17.50
    TEM
    -17.13
    ET
    -16.88
    (et
    -16.63
     Et
    -16.63
     mutual
    -16.50
    POSITIVE LOGITS
     Ken
    32.50
    Ken
    31.38
     Lego
    22.38
     Ep
    21.00
    ep
    20.25
     Gen
    20.00
    夏
    19.00
    	ep
    18.88
    (ep
    18.63
    Gen
    18.38
    Activations Density 0.022%

    No Known Activations