© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10887
    Prev
    Next
    INDEX
    Explanations

    economy and economies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æĭį
    -0.11
    èĬĴ
    -0.10
    輩
    -0.10
    heim
    -0.10
    çŃ·åŃIJ
    -0.09
    è¾Ł
    -0.09
    ä¸Ģ件
    -0.09
    éºĭ
    -0.09
    enser
    -0.09
    eous
    -0.09
    POSITIVE LOGITS
     economy
    0.18
     Economy
    0.17
    conomy
    0.15
    ç»ıæµİ
    0.13
    åĽ½æ°ijç»ıæµİ
    0.12
    欣
    0.12
    ç»ıæµİåıijå±ķ
    0.12
    ç»ıæµİå¢ŀéķ¿
    0.12
     economies
    0.12
     economÃŃa
    0.12
    Activations Density 0.212%

    No Known Activations