© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9670
    Prev
    Next
    INDEX
    Explanations

    tariffs on imports and exports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èŁ
    -0.08
    ruta
    -0.07
    ç¤
    -0.07
    åĪ°è´¦
    -0.07
     radix
    -0.07
    è¦ıç´Ħ
    -0.07
    ÑĤеÑĢи
    -0.06
    úm
    -0.06
     fid
    -0.06
    çļĦå¿ĥå¾Ĺ
    -0.06
    POSITIVE LOGITS
     exporters
    0.08
     WTO
    0.08
    åħ³ç¨İ
    0.08
     Imports
    0.08
    åľ£è¯ŀèĬĤ
    0.08
     exporter
    0.08
    补贴
    0.08
     export
    0.08
     retali
    0.08
    phan
    0.08
    Activations Density 0.032%

    No Known Activations