© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14714
    Prev
    Next
    INDEX
    Explanations

    say "place names"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     HttpRequest
    -16.25
    .UUID
    -15.06
    ManagedObject
    -14.75
    queeze
    -14.63
    .uuid
    -14.38
     autoFocus
    -14.38
     rugby
    -14.31
     enfer
    -14.19
    DECL
    -14.00
    (uuid
    -13.94
    POSITIVE LOGITS
    Michigan
    24.63
    合肥
    23.25
    安徽
    22.13
     Michigan
    21.25
     Illinois
    21.13
    武汉
    21.00
    Detroit
    20.13
    合肥市
    20.00
     Wisconsin
    19.75
    鄱
    19.63
    Activations Density 0.139%

    No Known Activations