© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14137
    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
    节点
    -17.00
    .Unlock
    -17.00
    _intersect
    -16.63
    Intersection
    -16.63
    stats
    -16.63
    揖
    -16.38
     stats
    -16.25
     đồ
    -16.13
    统计数据
    -16.13
    Charts
    -16.00
    POSITIVE LOGITS
     rég
    22.38
     Reg
    22.13
    ereg
    21.50
     REG
    20.75
     reg
    20.38
    _Reg
    20.25
    .reg
    20.25
    Reg
    20.00
    (reg
    20.00
    reg
    19.88
    Activations Density 0.154%

    No Known Activations