© 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. 2755
    Prev
    Next
    INDEX
    Explanations

    degree symbol

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

    No Comments

    Negative Logits
    乙
    -19.38
     legs
    -18.00
     Legs
    -17.00
    丙
    -17.00
    oux
    -16.88
     Pete
    -16.75
     Segment
    -16.63
    (props
    -16.63
    _SEGMENT
    -16.63
    文明
    -16.38
    POSITIVE LOGITS
    º
    47.75
     �
    45.25
    ’
    32.75
    �
    32.25
    ¦
    29.50
    ¹
    27.88
    ª
    25.50
    ¢
    24.63
    €
    24.50
    壹
    24.25
    Activations Density 0.018%

    No Known Activations