© 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. 51973
    Prev
    Next
    INDEX
    Explanations

    weather related terms

    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
    串
    -0.10
    åĪ»
    -0.10
    åŀ®
    -0.09
    åıªè§ģ
    -0.09
    нÑİ
    -0.09
    çľī
    -0.09
    é¦ĸåħĪæĺ¯
    -0.08
    çľ¼åīį
    -0.08
    æĪIJè´¥
    -0.08
    -components
    -0.08
    POSITIVE LOGITS
    èijŃ
    0.10
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.09
    çļĦä¸ĢäºĽ
    0.09
    /LICENSE
    0.08
    æĻ°
    0.08
    ç§ijåѦçłĶ究
    0.08
    .wr
    0.08
    ä¼ļç»Ļ
    0.08
    enda
    0.08
    NSS
    0.08
    Activations Density 0.023%

    No Known Activations