© 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. 886
    Prev
    Next
    INDEX
    Explanations

    say "stain" words

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

    No Comments

    Negative Logits
     breakfast
    -19.63
    饥
    -18.25
     Breakfast
    -18.00
    小吃
    -17.13
    饭
    -17.13
    diet
    -16.75
    早餐
    -16.75
    网站地图
    -16.63
     famine
    -16.63
    海岛
    -16.38
    POSITIVE LOGITS
     cy
    25.75
    .cy
    20.50
    cy
    20.38
    Cy
    20.00
     Cy
    19.25
     cyt
    18.50
     staining
    17.25
     tissue
    16.88
     stain
    16.25
     stained
    16.25
    Activations Density 0.110%

    No Known Activations