© 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. 20752
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common words

    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
    认è¯ĨåĪ°
    -0.09
    èİ·å¾ĹæĽ´å¤ļ
    -0.09
    ä½ķåĨµ
    -0.08
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.08
    å¨ĩ
    -0.08
    ä¸Ģæĸ¹éĿ¢
    -0.08
    ä¸ĭæĸ¹
    -0.08
    æŃ£å¦Ĥ
    -0.08
    able
    -0.08
    Indeed
    -0.08
    POSITIVE LOGITS
    æĪijå°±
    0.13
    æīĢ以æĪij
    0.12
    äºİæĺ¯æĪij
    0.11
    æĪijèĩªå·±
    0.11
    æĪij
    0.10
    äºİæĺ¯
    0.10
    ILES
    0.10
     bè
    0.09
    å¾Īæĺ¯
    0.09
    æĪijå¾Ī
    0.09
    Activations Density 0.090%

    No Known Activations