© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54534
    Prev
    Next
    INDEX
    Explanations

    news-related phrases

    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
    åĿIJèIJ½åľ¨
    -0.10
    æĻ®éĢļçļĦ
    -0.10
    æŃ£å¸¸çļĦ
    -0.10
    æ¾İæ¹ĥæĸ°éĹ»
    -0.09
    å½ĵåľ°çļĦ
    -0.09
    åīįæīĢ
    -0.09
    éļ¶å±ŀäºİ
    -0.09
    ä¾ĭå¤ĸ
    -0.09
    诸å¦Ĥ
    -0.09
    áŀ¶
    -0.09
    POSITIVE LOGITS
    ãģªãģľ
    0.09
    è°ĥæŁ¥æĺ¾ç¤º
    0.08
     Latest
    0.08
    otron
    0.08
    å°ĨæĪIJ为
    0.08
    èѦæĥķ
    0.08
    ‘
    0.07
    Bookmark
    0.07
    æĢİæł·
    0.07
    çłĶ究表æĺİ
    0.07
    Activations Density 0.274%

    No Known Activations