© 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. 2984
    Prev
    Next
    INDEX
    Explanations

    resident

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

    No Comments

    Negative Logits
    ,var
    -16.63
    usty
    -15.31
    sem
    -15.00
    etag
    -14.50
    culus
    -13.63
     Polar
    -13.50
    etics
    -13.38
    ephy
    -13.38
    鏡
    -13.31
     polar
    -13.25
    POSITIVE LOGITS
     resident
    72.50
    居民
    72.00
     residents
    70.00
     Resident
    68.50
    resident
    66.00
     Residents
    65.50
    Residents
    61.75
    Res
    60.00
    =res
    59.50
    [res
    59.50
    Activations Density 0.173%

    No Known Activations