© 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. 1249
    Prev
    Next
    INDEX
    Explanations

    humanities

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

    No Comments

    Negative Logits
    云南
    -22.00
    云南省
    -20.88
     torch
    -20.13
    =torch
    -19.38
    煤炭
    -18.13
    昆明
    -18.00
    torch
    -17.63
     Gson
    -17.50
    滇
    -17.38
     Torch
    -17.25
    POSITIVE LOGITS
    牛奶
    21.13
    	alpha
    20.00
    字母
    18.88
     Stock
    18.63
     creatively
    18.38
    电话
    17.88
    .alpha
    17.88
    阿根廷
    17.63
     Mafia
    17.50
    Alpha
    17.38
    Activations Density 0.422%

    No Known Activations