© 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. 2900
    Prev
    Next
    INDEX
    Explanations

    say reg

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

    No Comments

    Negative Logits
    annotate
    -17.75
    Annotations
    -16.63
    Annotation
    -16.25
    ˊ
    -16.25
    酥
    -15.88
     pole
    -15.50
    Reserved
    -15.13
     Pole
    -15.13
     annotate
    -14.94
    _annotations
    -14.75
    POSITIVE LOGITS
     reg
    82.00
     Reg
    65.00
    reg
    63.25
    	reg
    58.00
    (reg
    55.75
    Reg
    54.00
    .reg
    52.00
    _reg
    50.25
    /reg
    45.25
     regeneration
    44.25
    Activations Density 0.066%

    No Known Activations