© 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. 1052
    Prev
    Next
    INDEX
    Explanations

    say "police"

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

    No Comments

    Negative Logits
    盐
    -16.25
     Hindu
    -16.13
     Byte
    -16.13
    鹽
    -16.00
    gens
    -15.94
    Byte
    -15.56
     Tiền
    -15.25
     Sal
    -15.13
    脑
    -15.13
     Vim
    -14.81
    POSITIVE LOGITS
    pollo
    19.13
    警察
    16.13
     police
    15.81
    警方
    15.44
    ­i
    15.19
    刑警
    14.69
     Police
    14.56
    %n
    14.50
    周转
    14.25
    erte
    14.13
    Activations Density 0.092%

    No Known Activations