© 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. 51984
    Prev
    Next
    INDEX
    Explanations

    the followed by capitalized word

    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»ĸ们æĺ¯
    -0.10
    ä»ĸæĺ¯
    -0.10
    èĢģå¸ĪçļĦ
    -0.09
    loo
    -0.08
    建åħļ
    -0.08
    æį®äºĨ解
    -0.08
     Cheney
    -0.08
    éºĤ
    -0.08
    èĻ½è¯´
    -0.08
    assador
    -0.08
    POSITIVE LOGITS
    æľīåħ³éĥ¨éŨ
    0.13
    æĪijæĬĬ
    0.10
     authorities
    0.10
    缸åħ³éĥ¨éŨ
    0.10
    è¡·
    0.10
    ä¸ĢäºĽ
    0.09
    æľīåĩłä¸ª
    0.09
    æķĻèĤ²éĥ¨
    0.09
    æľ¬ç½ijç«Ļ
    0.09
    åѦä¼ļ
    0.09
    Activations Density 0.103%

    No Known Activations