© 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. 52163
    Prev
    Next
    INDEX
    Explanations

    text after common verbs

    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
    aban
    -0.09
    é¹ŀ
    -0.09
    è¾¹éĻħ
    -0.09
    wig
    -0.09
     margin
    -0.09
    èĨ¨
    -0.09
    åĤįæĻļ
    -0.09
    æ´
    -0.09
    olson
    -0.09
    游æĪıå½ĵä¸Ń
    -0.09
    POSITIVE LOGITS
    æŶä¸į
    0.09
    ä»Ĺ
    0.09
    åıªèĥ½
    0.08
    ä¸¥æł¼çļĦ
    0.08
    jec
    0.08
    ç´ł
    0.08
    åīįåIJİ
    0.08
    åıªæľī
    0.08
    秧
    0.08
    å°ıå¿ĥ翼翼
    0.08
    Activations Density 0.071%

    No Known Activations