© 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. 20570
    Prev
    Next
    INDEX
    Explanations

    typical residential

    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
    èĩªä»İ
    -0.10
    ä¸İä¼Ĺä¸įåIJĮ
    -0.10
    washer
    -0.09
    ä¸įåIJĮäºİ
    -0.09
    ä¸İä¼Ĺ
    -0.09
    äºĨ好åĩł
    -0.09
     vul
    -0.09
    è¦ģä¹Ī
    -0.09
    ACP
    -0.08
    ä¸Ģ缴åĪ°
    -0.08
    POSITIVE LOGITS
    å¹³åĿĩæ°´å¹³
    0.13
    æĥħåĨµä¸ĭ
    0.12
    ä¿Ŀå®Ī
    0.11
    çļĦæĥħåĨµä¸ĭ
    0.11
    èĢĮè¨Ģ
    0.10
    å¹³åĿĩ
    0.10
    æĿ¡ä»¶ä¸ĭ
    0.10
    åħ¸åŀĭ
    0.10
     typical
    0.10
    为ä¾ĭ
    0.10
    Activations Density 0.189%

    No Known Activations