© 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. 7930
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and millions/billions

    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
    常德
    -0.09
    å½ĵä»ĸ
    -0.09
    éĢģæĸĻ
    -0.08
    loth
    -0.08
    è·Łä»ĸ
    -0.08
    marvin
    -0.08
    çĶ¸
    -0.08
    ç®
    -0.08
    é«ĺ温
    -0.08
    符åIJĪæĿ¡ä»¶
    -0.08
    POSITIVE LOGITS
    éĩijé¢Ŀ
    0.10
    身价
    0.10
    æĢ»æĬķèµĦ
    0.10
     compliments
    0.09
    /boot
    0.09
    åįĥä¸ĩ
    0.09
    产åĢ¼
    0.09
    ä»·åĢ¼
    0.09
    éĺIJæĺİ
    0.09
    inia
    0.09
    Activations Density 0.083%

    No Known Activations