© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 924
    Prev
    Next
    INDEX
    Explanations

    say "x86 registers"

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

    No Comments

    Negative Logits
    惠州
    -22.50
    楚
    -20.13
    Singapore
    -19.75
     Canton
    -19.13
     Manila
    -18.88
    Php
    -18.75
     Flutter
    -18.75
     HK
    -18.63
     Singapore
    -18.63
    深圳市
    -18.50
    POSITIVE LOGITS
     AX
    19.25
    SI
    17.75
     Sussex
    17.13
    ax
    16.88
     SI
    15.94
     ax
    15.75
    �
    15.31
    ecx
    14.81
    oting
    14.75
    =ax
    14.75
    Activations Density 0.018%

    No Known Activations