© 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. 8908
    Prev
    Next
    INDEX
    Explanations

    mobile operating systems and devices

    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
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    ä¸ĢæĶ¯
    -0.09
    廪
    -0.09
    _HOR
    -0.08
    Spe
    -0.08
    æݼ
    -0.08
    ä¸ĢéĹ´
    -0.08
    äºĨ大éĩıçļĦ
    -0.08
    å°ı游æĪı
    -0.08
    楼ä¸ĭ
    -0.08
    POSITIVE LOGITS
    åIJİæŀľ
    0.10
    丼
    0.09
    ober
    0.09
    ä¸ĢçĤ¹åĦ¿
    0.09
    ä¹Łåı¯
    0.09
    æ»ļæ»ļ
    0.09
    éĺ¶
    0.08
    æį§
    0.08
    ungle
    0.08
     kuk
    0.08
    Activations Density 0.046%

    No Known Activations