© 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. 2745
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
     getApp
    -21.00
     Mem
    -20.63
     app
    -20.63
    (mem
    -20.38
     App
    -19.63
    	mem
    -19.50
     membr
    -18.75
     res
    -18.75
    app
    -18.50
    Mem
    -18.38
    POSITIVE LOGITS
     hundred
    54.00
    千
    52.00
    百
    50.25
     thousand
    49.75
     Hundred
    45.50
     million
    40.25
    一百
    39.00
     mill
    37.75
    万
    37.25
     Thousand
    37.00
    Activations Density 0.141%

    No Known Activations