© 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. 1223
    Prev
    Next
    INDEX
    Explanations

    Beijing

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

    No Comments

    Negative Logits
    北京
    -43.00
    京
    -39.25
     Beijing
    -36.25
    北京市
    -35.50
    在北京
    -34.50
     DC
    -33.00
    在京
    -32.75
     Washington
    -32.50
     dc
    -31.00
    京城
    -30.63
    POSITIVE LOGITS
    -php
    17.63
    _PHP
    16.38
    ijn
    16.00
    船上
    15.81
     Gamer
    15.81
    /php
    15.69
    (digits
    15.50
     '<?
    15.38
    造船
    15.31
     "<?
    15.19
    Activations Density 0.198%

    No Known Activations