© 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. 8730
    Prev
    Next
    INDEX
    Explanations

    that proves

    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
    ç»ıæŁ¥
    -0.10
    表çݰ为
    -0.09
     лиÑĩно
    -0.08
    å¥
    -0.08
    wood
    -0.08
    éĩįéĩį
    -0.08
    嬿
    -0.08
    æīĵäºĨ
    -0.07
    ä½ĵçİ°åľ¨
    -0.07
    åĪļåĪļ
    -0.07
    POSITIVE LOGITS
    ä¹İ
    0.10
    å¤©åĽ½
    0.10
    ä¸įå¿ĺ
    0.10
    æĤ¨åIJĮæĦı
    0.09
    åĴ±
    0.09
    forth
    0.09
    åľ¨æĦı
    0.09
    è¿«ä¸įåıĬå¾ħ
    0.09
    æIJģ
    0.09
    åı¯è§ģ
    0.09
    Activations Density 0.212%

    No Known Activations