© 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. 3010
    Prev
    Next
    INDEX
    Explanations

    say museum

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

    No Comments

    Negative Logits
    Comput
    -16.88
     COMPUT
    -16.75
     compute
    -16.25
     Compute
    -15.94
     deriv
    -15.81
     sounded
    -15.81
    Compute
    -15.44
     computing
    -15.44
    comput
    -15.06
     comput
    -14.88
    POSITIVE LOGITS
    馆
    69.00
    館
    57.50
    展馆
    42.50
    场馆
    40.00
     museum
    39.50
    Gen
    36.50
     GEN
    36.25
     Gen
    36.00
     gen
    35.00
    博物馆
    34.75
    Activations Density 0.046%

    No Known Activations