© 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. 15714
    Prev
    Next
    INDEX
    Explanations

    say "immune"

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

    No Comments

    Negative Logits
    pip
    -18.75
    dot
    -17.88
     pageIndex
    -17.00
    jen
    -17.00
    abra
    -17.00
    -dot
    -16.63
     Pip
    -16.50
     pipelines
    -16.38
     penal
    -16.38
    .pi
    -16.38
    POSITIVE LOGITS
     immune
    35.75
    免疫
    35.50
     immunity
    33.25
    immune
    32.75
    免疫力
    30.88
     Imm
    30.25
     immun
    29.88
    -imm
    27.38
     Immun
    27.25
    Imm
    27.00
    Activations Density 0.305%

    No Known Activations