© 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. 15432
    Prev
    Next
    INDEX
    Explanations

    say "medication"

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

    No Comments

    Negative Logits
     ballet
    -17.75
     bamboo
    -17.75
     Bauer
    -17.13
    建华
    -16.88
     debounce
    -16.88
    京剧
    -16.50
    httpClient
    -16.38
     Tango
    -16.13
    园林
    -16.13
     mountain
    -15.94
    POSITIVE LOGITS
    药
    34.75
    药师
    34.75
    药物
    34.75
    药品
    34.25
     medication
    33.00
     pharmacist
    32.75
     drug
    31.50
     medications
    31.38
     drugs
    30.88
     meds
    30.88
    Activations Density 0.289%

    No Known Activations