© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9703
    Prev
    Next
    INDEX
    Explanations

    in the middle of

    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
    é¢Ĩ
    -0.09
    ULER
    -0.09
    åĮł
    -0.08
    秦
    -0.08
    opsis
    -0.08
    à¸Ńà¸Ķ
    -0.08
     Kun
    -0.08
    æ´ŀå¯Ł
    -0.08
    alis
    -0.08
    é³Ŀ
    -0.08
    POSITIVE LOGITS
    缼å¼Ģ
    0.10
    æij¸ç´¢
    0.10
    广éĺĶ
    0.09
    éĽĨå¸Ĥ
    0.08
    ä¸Ģåľº
    0.08
    åķ¼
    0.08
    æĵ¦æĭŃ
    0.08
    称ä¹ĭ
    0.08
    å±ķåĮº
    0.08
    宽éĺĶ
    0.08
    Activations Density 0.010%

    No Known Activations