© 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. 61393
    Prev
    Next
    INDEX
    Explanations

    quantities with units or percentages

    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
    çªĴæģ¯
    -0.10
    éĢłç¦ı
    -0.09
    èĻ½çĦ¶æĺ¯
    -0.09
    èģĶåIJĪä¼ļ
    -0.09
    æĪªæŃ¢
    -0.08
    Ø´ÙĨ
    -0.08
    unci
    -0.08
    溧
    -0.08
    ä¿®
    -0.08
    éĺIJæĺİ
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·ä¸Ģ
    0.10
    æ¯ı天
    0.10
    ãģĻãĤĭãģ¨
    0.09
    çļĦè¯Ŀ
    0.09
    íķľëĭ¤ë©´
    0.09
     пом
    0.08
     tech
    0.08
     roughly
    0.08
     thì
    0.08
    天天
    0.08
    Activations Density 0.101%

    No Known Activations