© 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. 2642
    Prev
    Next
    INDEX
    Explanations

    say register

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

    No Comments

    Negative Logits
    -gen
    -21.63
     gen
    -21.38
     Gen
    -20.38
    .gen
    -19.25
    (gen
    -18.63
     req
    -18.38
     resolutions
    -18.00
    /gen
    -17.63
     Dean
    -17.50
    菰
    -17.38
    POSITIVE LOGITS
     register
    28.50
    (register
    28.00
     Register
    26.63
    _register
    26.00
    	register
    25.63
    register
    25.13
    Register
    24.50
    	Register
    23.75
    -register
    23.75
    REGISTER
    23.63
    Activations Density 0.149%

    No Known Activations