© 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. 52244
    Prev
    Next
    INDEX
    Explanations

    protest, rally, or lobby

    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
    太快
    -0.09
    ulos
    -0.09
    åī¯å±Ģéķ¿
    -0.09
    å¾Īæĥ³
    -0.09
    (env
    -0.09
    çļĦçIJĨæĥ³
    -0.09
    åıĹçĽĬ
    -0.09
    æīĵ交éģĵ
    -0.09
    æķij
    -0.08
    æįķé±¼
    -0.08
    POSITIVE LOGITS
    äºīåıĸ
    0.10
    åĽ¢ç»ĵ
    0.10
    æīĵèµ¢
    0.10
    ÑĢай
    0.09
    çŃĸçķ¥
    0.09
    æĪĺæľ¯
    0.09
    ä¾Ŀæ³ķ追究
    0.09
    åĿļåĨ³
    0.09
    åĪ¶æŃ¢
    0.09
    追究
    0.09
    Activations Density 0.104%

    No Known Activations