© 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. 2067
    Prev
    Next
    INDEX
    Explanations

    do not say register

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

    No Comments

    Negative Logits
    register
    -23.13
    	register
    -23.00
     register
    -22.88
    /register
    -22.63
     Morris
    -21.75
     registers
    -21.75
     Register
    -21.50
    注册
    -21.25
    -register
    -21.13
    @register
    -20.88
    POSITIVE LOGITS
     Rec
    16.88
    聿
    16.38
    (mut
    15.75
     Ep
    15.25
    (loc
    15.25
    loc
    15.19
     Ver
    15.06
    Rec
    14.63
     rec
    14.63
    �
    14.19
    Activations Density 0.223%

    No Known Activations