© 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. 20958
    Prev
    Next
    INDEX
    Explanations

    newspaper publisher

    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
    éĴĵé±¼
    -0.10
    å®ŀå¹²
    -0.10
    éĶ¦æłĩ
    -0.10
    åł°
    -0.09
    çī§
    -0.09
    绣
    -0.09
    æĹłåģ¿
    -0.09
    éħIJ
    -0.09
    è°¨æħİ
    -0.09
    å°ģéĹŃ
    -0.08
    POSITIVE LOGITS
    æĬ¥çº¸
    0.17
     Newspaper
    0.16
     newspapers
    0.14
    åį°åĪ·
    0.14
    æĬ¥ä¸ļ
    0.14
     newspaper
    0.14
     Newsp
    0.12
    æĹ¥æĬ¥
    0.11
    åį·
    0.11
    èIJ¥æĶ¶
    0.10
    Activations Density 0.184%

    No Known Activations