© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13969
    Prev
    Next
    INDEX
    Explanations

    herbal extracts

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

    No Comments

    Negative Logits
    投影
    -19.25
     projection
    -18.13
     Projection
    -17.63
    技术创新
    -17.50
    设施建设
    -17.25
    網絡
    -17.13
    projection
    -17.00
    投
    -16.75
    建设和
    -16.63
     Infrastructure
    -16.50
    POSITIVE LOGITS
    药材
    19.63
    提取
    19.00
     extraction
    17.25
     extracts
    17.25
     Extraction
    16.88
     remedies
    16.88
     Medic
    16.63
    芩
    16.63
    extract
    16.50
     extracted
    16.50
    Activations Density 0.534%

    No Known Activations