© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20540
    Prev
    Next
    INDEX
    Explanations

    customs, trade, tax, duty, tariff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¢Į
    -0.07
    court
    -0.06
    åľı
    -0.06
    ä¿Ŀ証
    -0.06
     sür
    -0.06
     Ry
    -0.06
    extend
    -0.06
    ÑĤÑģÑı
    -0.06
    erase
    -0.06
    æı¡çĿĢ
    -0.06
    POSITIVE LOGITS
    éĢļåħ³
    0.08
    èµ°ç§ģ
    0.07
    å®ŀçī©
    0.06
    åħ³
    0.06
    бÑĢан
    0.05
     ant
    0.05
    åħ³åį¡
    0.05
    éĹľ
    0.05
    ilar
    0.05
     Parlament
    0.05
    Activations Density 0.015%

    No Known Activations