© 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. 7914
    Prev
    Next
    INDEX
    Explanations

    context of reasons and decisions

    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
    ä¸įæ¸ħæ¥ļ
    -0.10
     lazy
    -0.09
    pio
    -0.09
    åħ¥ãĤĬ
    -0.09
    à¹ĥส
    -0.08
    åŨ
    -0.08
    æį¨ãģ¦
    -0.08
    丰å¯Į
    -0.08
    à¹ģà¸Ľà¸¥à¸ģ
    -0.08
     hed
    -0.08
    POSITIVE LOGITS
    ä¸įåĨį
    0.13
    åıijå±ķ空éĹ´
    0.13
    太å¤ļçļĦ
    0.12
    æ¸IJ
    0.11
    åĨįä¹Ł
    0.11
    åĨįä¹Łæ²¡æľī
    0.11
    ä¸įèĥ½åĨį
    0.10
    没æľīåĬŀæ³ķ
    0.10
    å®ŀåľ¨æĺ¯å¤ª
    0.10
    çŃīåİŁåĽł
    0.10
    Activations Density 0.137%

    No Known Activations