© 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. 50105
    Prev
    Next
    INDEX
    Explanations

    Taiwan, health insurance, northern, southern

    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
    å¹²ä»Ģä¹Ī
    -0.11
    è¯ŀ
    -0.10
    ابت
    -0.10
    å°±é¤IJ
    -0.10
    饮
    -0.10
    æİ¥åħ¥
    -0.09
    ä¸ĵ家ç»Ħ
    -0.09
    åģļé¥Ń
    -0.09
    å¼Ģåĩº
    -0.09
    æľĪæľ«
    -0.09
    POSITIVE LOGITS
    é«ĺéĽĦ
    0.16
    åŁĶ
    0.15
    èįĸ
    0.15
    åı°æ¹¾
    0.14
     Taiwan
    0.14
    åı°åĮĹ
    0.14
     Taipei
    0.13
    ãĦ§
    0.13
     Taiwanese
    0.13
    å¡ijèĥ¶
    0.12
    Activations Density 0.203%

    No Known Activations