© 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. 8195
    Prev
    Next
    INDEX
    Explanations

    another item or another function

    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
    éĹ¯
    -0.10
    ä½łæĥ³
    -0.09
    ç«ł
    -0.08
     Bian
    -0.08
    _drv
    -0.08
    omez
    -0.08
    æ¸ł
    -0.08
     parameter
    -0.07
    ichtet
    -0.07
    åIJ¬åĬĽ
    -0.07
    POSITIVE LOGITS
    éĻĩ
    0.11
    åĪ¥ãģ®
    0.11
    æĦıä¹īä¸ĬçļĦ
    0.11
    åIJĮç±»
    0.11
    å½¼æѤ
    0.10
    ä¸įå¼Ģ
    0.10
    äºĴ缸
    0.10
    å¯Ŀ
    0.10
    æī¹åıij
    0.10
    æĸ°éĻĪ代谢
    0.10
    Activations Density 0.157%

    No Known Activations