© 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. 15513
    Prev
    Next
    INDEX
    Explanations

    say meds

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

    No Comments

    Negative Logits
    进球
    -19.00
    _local
    -19.00
     Local
    -18.88
    _locale
    -18.88
     local
    -18.75
    球场
    -18.63
     localized
    -18.50
    庭院
    -18.50
     LOCAL
    -18.38
     locales
    -18.25
    POSITIVE LOGITS
     meds
    16.25
    医
    15.44
    med
    15.06
    砒
    14.81
    Med
    14.44
     medications
    14.25
     medication
    14.19
     med
    14.13
     medical
    14.06
    -dr
    14.06
    Activations Density 0.321%

    No Known Activations