© 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. 7730
    Prev
    Next
    INDEX
    Explanations

    Neptune astrological associations

    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
    æݨä»ĭ
    -0.10
    åħ¥å¸Ĥ
    -0.10
    讳
    -0.10
    åı¯è°ĵæĺ¯
    -0.09
    åIJ®
    -0.08
    è°Ĵ
    -0.08
    åĽ¢åľĨ
    -0.08
    è¾Ħ
    -0.08
    æĽ´å¥½çļĦ
    -0.08
    称åij¼
    -0.08
    POSITIVE LOGITS
    åģ¶çĦ¶
    0.09
     cet
    0.08
    å®ĺæĸ¹å¾®ä¿¡
    0.08
     Hamp
    0.08
    uç
    0.08
    /www
    0.08
    egot
    0.08
    æ¯ı天éĥ½
    0.08
    ddit
    0.08
    è¿Ļæĺ¯æĪij
    0.08
    Activations Density 0.059%

    No Known Activations