© 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. 9149
    Prev
    Next
    INDEX
    Explanations

    our, we, us, ourselves

    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
    å¸®ä½ł
    -0.11
    ä½łèĥ½
    -0.10
    ä½łè¦ģ
    -0.10
    ç»Ļä½ł
    -0.09
    å¯¹ä½ł
    -0.09
     you
    -0.09
    ä½ł
    -0.09
    ä¼ļè®©ä½ł
    -0.09
    è°¢è°¢ä½ł
    -0.09
    æĪijå½ĵæŶ
    -0.09
    POSITIVE LOGITS
     ourselves
    0.18
    å½ĵæĪij们
    0.16
    å¦ĤæŀľæĪij们
    0.15
    æĪij们å¿ħé¡»
    0.15
    æĪij们éľĢè¦ģ
    0.15
    æĺ¯æĪij们
    0.15
    æĪij们åºĶ该
    0.13
    åĽłä¸ºæĪij们
    0.12
    åħ³äºİæĪij们
    0.12
    æĪij们ä¼ļ
    0.12
    Activations Density 0.124%

    No Known Activations