© 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. 3105
    Prev
    Next
    INDEX
    Explanations

    say "camera"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    排毒
    -22.88
     diarrhea
    -21.50
    白糖
    -20.38
    献血
    -20.25
    股民
    -20.25
    每股
    -19.88
    腹泻
    -19.88
     diarr
    -19.75
     sweating
    -19.50
    支行
    -19.50
    POSITIVE LOGITS
    相机
    19.75
     camera
    19.63
    PointCloud
    19.50
     Lid
    19.38
    (cam
    19.25
     Camera
    18.38
    (Camera
    18.13
     CAMERA
    18.00
     cam
    17.75
    cam
    17.63
    Activations Density 0.059%

    No Known Activations