© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1261
    Prev
    Next
    INDEX
    Explanations

    confidential information

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

    No Comments

    Negative Logits
    商业
    -34.00
     商
    -29.50
    商
    -27.00
    商業
    -26.75
    商人
    -25.75
    商业化
    -25.50
    商场
    -24.50
     comerc
    -24.25
    商务
    -24.00
     commercial
    -23.88
    POSITIVE LOGITS
    保罗
    18.88
     Paul
    16.50
    Paul
    16.00
     paul
    15.88
    蛋白
    15.75
     Luk
    15.63
     Paulo
    15.63
    sock
    15.50
    泪
    15.25
    	sql
    14.94
    Activations Density 0.150%

    No Known Activations