© 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. 3236
    Prev
    Next
    INDEX
    Explanations

    domain

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    支线
    -14.75
    倮
    -14.44
     plate
    -14.06
    venient
    -13.38
    alon
    -13.38
    duk
    -13.38
    razier
    -13.00
    emi
    -12.94
    omi
    -12.94
     lamp
    -12.88
    POSITIVE LOGITS
     domain
    81.00
    domain
    76.00
     Domain
    70.50
    Domain
    69.50
    _domain
    67.50
    (domain
    66.50
    -domain
    62.25
    领域
    62.00
     domains
    59.50
    .domain
    56.50
    Activations Density 0.089%

    No Known Activations