© 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. 2255
    Prev
    Next
    INDEX
    Explanations

    say "regime"

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

    No Comments

    Negative Logits
    乙
    -19.63
    ungi
    -17.63
    丁
    -16.75
    .serial
    -16.00
    (Util
    -15.88
    .ravel
    -15.00
     Knot
    -14.56
     SEC
    -14.56
    inka
    -14.44
    rai
    -14.38
    POSITIVE LOGITS
     regime
    66.50
     Reg
    64.00
     reg
    59.75
    Reg
    58.25
    reg
    57.25
     regimes
    56.50
    	reg
    55.25
    (reg
    52.50
    _reg
    51.50
    -reg
    50.75
    Activations Density 0.056%

    No Known Activations