© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    drug/alcohol

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

    No Comments

    Negative Logits
    酒
    -19.00
    饮
    -17.25
    drug
    -16.63
     drug
    -16.00
     Drug
    -15.94
     log
    -14.50
     Marl
    -14.44
    打球
    -14.31
     drink
    -14.25
     drinkers
    -14.00
    POSITIVE LOGITS
    меди
    21.13
    Ak
    20.00
    AI
    19.13
     меди
    19.00
     Artificial
    19.00
     Po
    18.88
     Akron
    18.75
     artificial
    18.75
     AI
    18.25
     Ak
    18.13
    Activations Density 0.291%

    No Known Activations