© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21068
    Prev
    Next
    INDEX
    Explanations

    to offer or do

    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
    æľīä¸Ģå®ļçļĦ
    -0.10
    å¤ļ彩
    -0.09
    arendra
    -0.09
    ä¿ļ
    -0.09
    让ç͍æĪ·
    -0.09
     Loves
    -0.09
    ilm
    -0.08
     rá»Ŀi
    -0.08
    åIJį声
    -0.08
    è·Łéļı
    -0.08
    POSITIVE LOGITS
    RN
    0.10
    ä¸įæķ¢
    0.09
    ç¾ģ
    0.08
    å¿ı
    0.08
    PEG
    0.08
    èĻŀ
    0.08
    èIJ½åIJİ
    0.08
     instrumental
    0.08
    åı¯èĥ½ä¼ļ
    0.08
    yla
    0.08
    Activations Density 0.009%

    No Known Activations