© 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. 36642
    Prev
    Next
    INDEX
    Explanations

    gathered or shared

    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
    è¿ŀ线
    -0.10
    æŃ£å¼ı
    -0.10
    .va
    -0.10
    èµ°åİ»
    -0.10
    ä»»ä½ķ
    -0.10
    åĴĮä»ĸçļĦ
    -0.09
    æ¾Ī
    -0.09
    eto
    -0.09
    éĻªä¼´
    -0.09
    大家åı¯ä»¥
    -0.09
    POSITIVE LOGITS
    åIJĦèĩª
    0.19
     themselves
    0.18
    åIJĦèĩªçļĦ
    0.16
    纷纷
    0.15
    å½¼æѤ
    0.13
    纷纷表示
    0.12
    é½IJèģļ
    0.11
    ä¸Ģèĩ´
    0.11
    ä¹Łéĥ½
    0.10
    åľ¨ä¸Ģèµ·
    0.10
    Activations Density 0.213%

    No Known Activations