© 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. 7739
    Prev
    Next
    INDEX
    Explanations

    lists of software or hardware

    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
    äºĮèĥİ
    -0.10
    é¢ĺ主
    -0.10
    ä¸įè§ģäºĨ
    -0.09
    交ç»Ļ
    -0.08
    ä¹ĭä½ľ
    -0.08
    ä¸įåĩºæĿ¥
    -0.08
    åľ¨åľ°ä¸Ĭ
    -0.08
    æīĭæĦŁ
    -0.08
    æ¿ĢåĬ¨
    -0.08
    è§ĤçĤ¹
    -0.08
    POSITIVE LOGITS
    çī¹æľīçļĦ
    0.11
    ä¸ĬçļĦ
    0.10
    ä¸ĵ享
    0.09
    çݯå¢ĥä¸ĭ
    0.09
     Trent
    0.09
    éĺµèIJ¥
    0.09
    çĭ¬æľīçļĦ
    0.09
    å¹³åı°ä¸Ĭ
    0.08
    tridges
    0.08
     prelim
    0.08
    Activations Density 0.465%

    No Known Activations