© 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. 37099
    Prev
    Next
    INDEX
    Explanations

    exercise and fitness metrics

    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
    èĨĢ
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    åħī线
    -0.08
    æ¼ı
    -0.08
    麻çĹ¹
    -0.08
    æ¸ĹéĢı
    -0.08
    åĺ¹
    -0.08
    headed
    -0.08
    zek
    -0.08
    æĥ³èµ·æĿ¥
    -0.08
    POSITIVE LOGITS
    obil
    0.10
    ç«ŀæĬĢ
    0.10
    彩
    0.10
    afari
    0.09
    éªĦ
    0.09
    InstanceOf
    0.09
    åıĹçĽĬ
    0.08
    综èīºèĬĤ缮
    0.08
    ovic
    0.08
    æĹłå½¢
    0.08
    Activations Density 0.170%

    No Known Activations