© 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. 3306
    Prev
    Next
    INDEX
    Explanations

    say "label"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     course
    -17.13
    -course
    -16.63
    course
    -16.63
    ancellable
    -15.88
    TL
    -15.63
    LOB
    -15.13
    Course
    -15.06
    LAS
    -15.06
     COMPANY
    -14.88
    佗
    -14.75
    POSITIVE LOGITS
     label
    66.50
    label
    59.75
    (label
    59.00
     Label
    57.00
    Label
    56.50
    	label
    55.50
    .label
    55.25
    _label
    54.75
    =label
    49.00
    ,label
    48.75
    Activations Density 0.126%

    No Known Activations