© 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. 1331
    Prev
    Next
    INDEX
    Explanations

    [equipment] => [equipment]

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

    No Comments

    Negative Logits
     equipment
    -46.50
     Equipment
    -43.50
    Equipment
    -42.25
    equipment
    -42.00
    设备
    -40.00
     Equip
    -38.75
     equip
    -37.50
    Equip
    -36.75
     equipments
    -36.00
    装备
    -35.50
    POSITIVE LOGITS
    python
    19.25
     Python
    17.88
    -python
    17.75
     Mathematic
    16.25
    (math
    15.88
     python
    15.63
    伽
    15.50
    orpion
    15.19
    Python
    15.00
     mathematic
    14.81
    Activations Density 0.081%

    No Known Activations