© 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. 37453
    Prev
    Next
    INDEX
    Explanations

    seasons

    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
    å¤ļä¹Ī
    -0.09
    mium
    -0.09
    ä»ĬçĶŁ
    -0.09
    æĺ¯å¤ļä¹Ī
    -0.09
    éĻ¤å¤ķ
    -0.09
    _supported
    -0.08
    æĺİ天
    -0.08
    erah
    -0.08
    åħ¶æ¬¡
    -0.08
    ä¸ĭåij¨
    -0.08
    POSITIVE LOGITS
    à¹ĥหà¸į
    0.09
    igin
    0.09
    åĬª
    0.09
    æŶèĬĤ
    0.09
    å·¥ä½ľæĬ¥åijĬ
    0.08
    åĩłä¸ªæľĪ
    0.08
    çļĦåIJĪä½ľ
    0.08
     bÄĻd
    0.08
    åĬ¿å¤´
    0.08
    uck
    0.08
    Activations Density 0.020%

    No Known Activations