© 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. 52281
    Prev
    Next
    INDEX
    Explanations

    introducing good fortune

    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
    究竣
    -0.11
    åĪ°åºķ
    -0.10
    åı¯èĥ½åıijçĶŁ
    -0.10
    å¦Ĥä½ķ
    -0.10
    ä¸įç¦ģ
    -0.09
    ç®ĢçĽ´å°±æĺ¯
    -0.09
    该å¦Ĥä½ķ
    -0.08
    æĺ¯å¦Ĥä½ķ
    -0.08
    æĮĩæľĽ
    -0.08
     ngá»Ŀ
    -0.08
    POSITIVE LOGITS
    ä¹Łæľīä¸ĢäºĽ
    0.10
    æľī个
    0.10
     (?)
    0.09
    æľīä¸ĢäºĽ
    0.09
    èĮ¬
    0.09
    æľīäºĽ
    0.09
    ä¹İ
    0.09
    æľīä¸Ģ个
    0.08
    æľīå¾Īå¤ļ
    0.08
    æĪij们çļĦ
    0.08
    Activations Density 0.146%

    No Known Activations