© 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. 1337
    Prev
    Next
    INDEX
    Explanations

    NSAID drugs

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

    No Comments

    Negative Logits
     Ip
    -35.25
     IP
    -33.50
    IP
    -32.75
    Ip
    -32.75
    _IP
    -32.25
    /IP
    -31.13
    免疫
    -29.00
     ice
    -28.88
     IPs
    -28.63
    _ip
    -28.50
    POSITIVE LOGITS
    股票
    14.63
    acle
    14.00
    港
    13.75
    obot
    13.63
     retarded
    13.44
    松
    13.31
    пуска
    13.13
    htar
    12.94
     FAG
    12.88
    风
    12.75
    Activations Density 0.695%

    No Known Activations