© 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. 2373
    Prev
    Next
    INDEX
    Explanations

    say "args"

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

    No Comments

    Negative Logits
    [param
    -19.75
    (prop
    -18.50
    (param
    -18.38
    ,opt
    -18.38
    保
    -17.13
    (opt
    -17.00
    (segment
    -16.13
    _Param
    -16.00
    	param
    -15.69
    [arg
    -15.50
    POSITIVE LOGITS
    =params
    41.75
     args
    39.75
    (args
    39.75
     nums
    39.75
    (params
    39.50
    =args
    38.50
    nums
    38.25
    [args
    37.25
    params
    37.25
    args
    37.00
    Activations Density 0.595%

    No Known Activations