© 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. 2165
    Prev
    Next
    INDEX
    Explanations

    say 居民

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

    No Comments

    Negative Logits
    facility
    -19.00
     Facility
    -18.88
     Facilities
    -18.75
     facilities
    -17.50
     facility
    -17.25
    fac
    -15.81
     verde
    -15.69
    	ref
    -15.63
    repos
    -15.19
    herits
    -15.13
    POSITIVE LOGITS
     res
    29.13
     Res
    28.50
    Res
    28.25
    居民
    27.88
    (res
    26.25
    .res
    24.63
    	res
    24.50
    _res
    24.25
     RES
    24.13
    -res
    23.75
    Activations Density 0.029%

    No Known Activations