© 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. 3206
    Prev
    Next
    INDEX
    Explanations

    say service

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (serv
    -20.38
    (sv
    -19.00
     chapter
    -18.38
    章
    -17.25
     array
    -16.88
    数组
    -16.88
    chapter
    -16.75
    蚕
    -16.50
    Chapter
    -16.38
     chapters
    -15.81
    POSITIVE LOGITS
     service
    42.25
    service
    39.50
     Service
    36.00
    Service
    35.75
    _service
    33.50
    	service
    32.00
    服务
    31.63
    -service
    31.25
    .service
    28.25
    (service
    28.00
    Activations Density 0.052%

    No Known Activations