© 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. 3123
    Prev
    Next
    INDEX
    Explanations

    say current

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     label
    -22.38
    道
    -20.00
    [label
    -19.88
    	label
    -19.75
    (label
    -19.75
    =label
    -19.75
    标签
    -19.50
     organization
    -18.25
    label
    -18.25
    组织
    -18.13
    POSITIVE LOGITS
    current
    51.75
     current
    51.00
    Current
    44.75
     Current
    44.25
    (current
    44.00
    电流
    43.00
    =current
    42.75
    .current
    42.25
    _current
    40.75
    [current
    39.50
    Activations Density 0.163%

    No Known Activations