© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15380
    Prev
    Next
    INDEX
    Explanations

    say chemical

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

    No Comments

    Negative Logits
     Tower
    -21.38
    Tower
    -18.63
     Towers
    -18.50
     towers
    -17.88
     tower
    -17.25
    寺院
    -16.50
    tower
    -16.50
    iosk
    -16.00
    .Site
    -15.88
    .Accessible
    -15.75
    POSITIVE LOGITS
     chemical
    58.00
    化学
    57.00
     chemistry
    56.00
    Chem
    55.00
     chem
    54.00
    chemical
    54.00
     chemicals
    53.50
     Chemical
    53.25
     Chem
    52.50
     Chemistry
    52.00
    Activations Density 0.314%

    No Known Activations