© 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. 51726
    Prev
    Next
    INDEX
    Explanations

    before concluding action

    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
    æĪijå½ĵæŶ
    -0.09
    å½ĵæŶ
    -0.09
    èīº
    -0.08
    çIJī
    -0.08
    éĦł
    -0.08
    éĤĢ
    -0.08
    orama
    -0.08
    æ¾İæ¹ĥ
    -0.07
     наблÑİ
    -0.07
    æ£ł
    -0.07
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.11
    åıĺå¾ĹæĽ´
    0.10
     ÑĢаÑģÑħод
    0.10
    ä¸ĭ次
    0.10
    èĨı
    0.10
    åĽŀåİ»
    0.10
    è¿Ľä¸ĢæŃ¥
    0.10
    æĪ´ä¸Ĭ
    0.10
    æĽ´å¤§
    0.10
    继ç»Ń
    0.10
    Activations Density 0.020%

    No Known Activations