© 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. 51920
    Prev
    Next
    INDEX
    Explanations

    shops and culinary events

    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
    ardi
    -0.09
    esk
    -0.09
    è¿Ļ个游æĪı
    -0.09
    产åĩº
    -0.08
    ä¸įæħİ
    -0.08
    æĺĤ
    -0.08
    èĢģ大
    -0.08
    天天
    -0.08
    æĪĽ
    -0.08
    alia
    -0.08
    POSITIVE LOGITS
    ç¼Ĺ
    0.10
    å¸ĪçĶŁ
    0.09
    çļĦæŶéĹ´éĩĮ
    0.09
    大家åı¯ä»¥
    0.09
    å±ĬæŶ
    0.09
     Kosten
    0.09
    轸
    0.09
    å·¡åĽŀ
    0.09
    æīĢæıIJä¾Ľ
    0.09
    ä¹ĭæīĢ
    0.09
    Activations Density 0.018%

    No Known Activations