© 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. 2936
    Prev
    Next
    INDEX
    Explanations

    say "registry"

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

    No Comments

    Negative Logits
    (Util
    -17.38
    reserved
    -15.88
     Qual
    -15.88
    保
    -15.81
     reserved
    -15.63
     qual
    -15.50
    发
    -15.19
     Reserve
    -15.00
    _ATT
    -14.94
     cap
    -14.81
    POSITIVE LOGITS
     registry
    50.00
     Registry
    47.25
    Registry
    45.50
    registry
    45.50
    (reg
    43.00
    _registry
    40.50
    .Registry
    39.75
    _REGISTRY
    39.50
     reg
    38.25
     regist
    37.50
    Activations Density 0.048%

    No Known Activations