© 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. 2206
    Prev
    Next
    INDEX
    Explanations

    regulation

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

    No Comments

    Negative Logits
     Mut
    -19.63
     mut
    -19.50
     configs
    -18.00
    Configs
    -17.75
     dist
    -17.63
     cap
    -17.50
     Seg
    -16.88
     Cap
    -16.88
     config
    -16.75
     ref
    -16.25
    POSITIVE LOGITS
    条例
    41.00
    条
    33.50
     Regulation
    28.63
    ereg
    28.13
     REG
    27.63
    -reg
    27.50
    條
    27.50
     regulation
    27.50
    Reg
    27.38
    REG
    27.00
    Activations Density 0.022%

    No Known Activations