© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    citrus fruits

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

    No Comments

    Negative Logits
    橘
    -22.63
    鲈
    -21.25
    Florida
    -20.88
     citrus
    -20.75
    柑
    -20.25
     Florida
    -20.25
    芬兰
    -18.13
     oranges
    -17.38
    Python
    -17.13
    PYTHON
    -17.13
    POSITIVE LOGITS
    云
    20.88
    羊
    20.13
     clouds
    20.00
     energy
    19.88
    energy
    18.88
     cloud
    18.63
    xFD
    18.50
    story
    18.38
    故事
    18.38
     story
    18.13
    Activations Density 0.296%

    No Known Activations