© 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. 51991
    Prev
    Next
    INDEX
    Explanations

    yesterday, week, night, morning, tonight

    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
    髹
    -0.09
    é¦ĸ缸
    -0.09
    æľ¬æĬ¥
    -0.08
    æĮĩåIJij
    -0.08
    èĢģ人家
    -0.08
    æıIJä¾ĽæĽ´å¤ļ
    -0.08
    ä¸ĸçķĮç»ıæµİ
    -0.08
    çļĦèĥĮåIJİ
    -0.08
    reve
    -0.08
    æ»Ķ
    -0.08
    POSITIVE LOGITS
    Mate
    0.09
    éĹ²
    0.09
    æĪijå°±
    0.09
    åĩłæ¬¡
    0.08
    大åѦ
    0.08
    _util
    0.08
    æľī幸
    0.08
    èĥĨ
    0.08
    æĽ´æĺ¯
    0.08
    ç®Ģ缴æĺ¯
    0.08
    Activations Density 0.095%

    No Known Activations