© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 852
    Prev
    Next
    INDEX
    Explanations

    say Khmer letters

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

    No Comments

    Negative Logits
     Wyoming
    -24.88
    Pakistan
    -22.38
    India
    -21.25
     Pakistani
    -20.25
     Nebraska
    -20.25
     Pakistan
    -20.25
    巴基斯坦
    -20.00
     India
    -19.50
    甘肃省
    -19.38
    新西兰
    -19.13
    POSITIVE LOGITS
    沈阳
    20.75
     Qi
    19.25
    icot
    19.13
    ឋ
    19.13
    �
    19.00
    ICI
    19.00
    DIC
    18.75
    (IC
    18.75
    NavController
    18.50
     Catalan
    18.38
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.