© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15792
    Prev
    Next
    INDEX
    Explanations

    say "protein"

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

    No Comments

    Negative Logits
    万户
    -19.25
    commands
    -18.25
    command
    -17.63
    totalCount
    -17.38
    .command
    -17.25
    司令
    -17.00
    /command
    -16.63
    .Command
    -16.50
     command
    -16.38
    _MED
    -16.38
    POSITIVE LOGITS
    蛋白
    38.00
     protein
    37.00
    蛋白质
    35.00
    protein
    34.75
     Protein
    33.00
     proteins
    32.25
     Prote
    30.25
     prote
    27.88
     amino
    23.50
    氨基酸
    23.25
    Activations Density 0.215%

    No Known Activations