© 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. 51449
    Prev
    Next
    INDEX
    Explanations

    it gives

    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
    éĻĽ
    -0.10
    baugh
    -0.09
     коÑĤоÑĢ
    -0.09
    ä¹Łå°±æĺ¯
    -0.08
    èĩªçĦ¶èĢĮ
    -0.08
     Rosen
    -0.08
    ger
    -0.08
    å°¤åħ¶æĺ¯
    -0.08
    uzzi
    -0.08
    æľīæĦı
    -0.08
    POSITIVE LOGITS
    ç§Łè½¦
    0.10
    åĬ¨éĿĻ
    0.09
    æµģåIJij
    0.08
    éľģ
    0.08
    è±ļ
    0.08
    æݥ管
    0.08
    çĿ¿
    0.08
    触åıĬ
    0.08
    rah
    0.08
    æ³Ĺ
    0.08
    Activations Density 0.512%

    No Known Activations