© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16341
    Prev
    Next
    INDEX
    Explanations

    say proteins

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

    No Comments

    Negative Logits
    木
    -17.50
    硬
    -17.38
    Hard
    -16.75
    hard
    -16.25
     Tiles
    -16.00
    寂静
    -15.94
    箱子
    -15.38
    ington
    -15.38
    硬化
    -15.13
    .tiles
    -15.06
    POSITIVE LOGITS
     proteins
    24.00
    蛋白质
    23.25
     protein
    22.38
    protein
    22.25
     Protein
    21.38
     chemicals
    21.38
    蛋白
    21.38
     molecules
    20.63
    分子
    19.63
     molecule
    19.50
    Activations Density 0.152%

    No Known Activations