© 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. 14992
    Prev
    Next
    INDEX
    Explanations

    say "hospital"

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

    No Comments

    Negative Logits
    yb
    -17.00
    yw
    -15.75
    马拉
    -15.50
    螽
    -15.50
    probe
    -15.38
    例子
    -15.06
    嘏
    -14.88
    يك
    -14.81
    immer
    -14.75
    ystick
    -14.75
    POSITIVE LOGITS
     hospital
    18.50
    hospital
    17.50
    医院
    16.88
    人民医院
    16.50
    贰
    15.88
    该院
    15.63
    国际机场
    14.56
     hospitals
    14.56
    紧急
    14.50
    atta
    14.44
    Activations Density 0.059%

    No Known Activations