© 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. 2516
    Prev
    Next
    INDEX
    Explanations

    say residence

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

    No Comments

    Negative Logits
     ethical
    -21.00
     eth
    -20.63
    递
    -19.75
     Eth
    -19.13
    伦理
    -18.63
     ethics
    -18.50
    Recursive
    -18.50
     recursive
    -18.25
    套
    -18.25
     ethic
    -17.75
    POSITIVE LOGITS
    驻
    53.75
    駐
    43.75
     Residence
    21.00
    Par
    19.88
    进驻
    19.63
    寓
    18.88
     residence
    18.88
     Par
    18.75
    派驻
    18.63
     par
    18.38
    Activations Density 0.031%

    No Known Activations