© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1953
    Prev
    Next
    INDEX
    Explanations

    [vision] => [drug]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    visual
    -35.50
    视觉
    -34.50
     visual
    -34.50
    Visual
    -33.50
     Visual
    -32.00
     visualize
    -31.38
     visuals
    -29.38
     Vision
    -29.00
     vision
    -28.75
    _visual
    -28.63
    POSITIVE LOGITS
     drug
    26.75
    药物
    25.50
     drugs
    24.50
     Drug
    24.38
    Drug
    22.75
     Drugs
    21.88
    drug
    21.00
    药
    19.75
    卡
    18.75
     Lancaster
    18.50
    Activations Density 0.114%

    No Known Activations