© 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. 444
    Prev
    Next
    INDEX
    Explanations

    say Chinese dynasties

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

    No Comments

    Negative Logits
    台风
    -20.00
    饮用水
    -19.75
    单车
    -19.75
    艇
    -19.25
    UF
    -19.25
    (pf
    -19.13
    PF
    -19.13
     PF
    -19.13
     Rotterdam
    -18.63
    饮料
    -18.63
    POSITIVE LOGITS
     Qin
    23.13
    秦
    20.38
     Chinese
    19.75
    隋
    19.63
     Xia
    19.38
    汉族
    19.25
     Yuan
    19.00
     China
    18.63
     chinese
    18.50
     Zhu
    18.50
    Activations Density 0.259%

    No Known Activations