© 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. 20867
    Prev
    Next
    INDEX
    Explanations

    any fashion or purpose

    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
    æĮº
    -0.09
    èĬ¸
    -0.09
    åħ¨ç¨ĭ
    -0.08
    ä¸ĵçĶ¨
    -0.08
    éŃĤ
    -0.08
    åIJĮèĥŀ
    -0.08
    åĹĶ
    -0.08
     repl
    -0.08
    åĶ¯ä¸ĢçļĦ
    -0.08
    仡
    -0.08
    POSITIVE LOGITS
    åĩī
    0.10
    åĩºèĩª
    0.10
    æīĵçĿĢ
    0.10
    æĦıä¹īä¸Ĭ
    0.09
    æ´Ĺ
    0.09
    hone
    0.09
    涼
    0.09
    urator
    0.08
    æĪijä»¬çŁ¥éģĵ
    0.08
    éĺij
    0.08
    Activations Density 0.009%

    No Known Activations