© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20960
    Prev
    Next
    INDEX
    Explanations

    trade wars and imbalance

    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
    æľīç§į
    -0.10
    豪éŨ
    -0.09
    æľ½
    -0.09
    æĶ¶åĪ°äºĨ
    -0.09
    å¹³åĩ¡
    -0.09
    ç«Ł
    -0.08
    æĻĸ
    -0.08
    楸
    -0.08
    æݼ
    -0.08
    ä¾Ľæ±Ĥ
    -0.08
    POSITIVE LOGITS
    è°ĥæķ´
    0.10
    注å®ļ
    0.10
    å¾Īéķ¿æŶéĹ´
    0.09
    æĪĺå½¹
    0.09
    ç»ĵæŀĦè°ĥæķ´
    0.09
    éģı
    0.09
    調æķ´
    0.09
     Contributor
    0.09
     adjustment
    0.09
    éķ¿æķĪ
    0.09
    Activations Density 0.044%

    No Known Activations