© 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. 52621
    Prev
    Next
    INDEX
    Explanations

    heart, lung, liver, kidney transplantation

    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
    伤
    -0.10
    æĭĺ
    -0.10
    弩
    -0.10
    æįī
    -0.09
    æĭĹ
    -0.09
    æĶ¶éĽĨ
    -0.09
     Carroll
    -0.09
    åĩłåı¥
    -0.09
    仿
    -0.09
    æŃ£å¼ı
    -0.08
    POSITIVE LOGITS
    æĽ¦
    0.11
    éĢļæĬ¥
    0.10
    åģļå®Į
    0.09
    .experimental
    0.08
    вед
    0.08
    راس
    0.08
    mailbox
    0.08
    	ts
    0.08
    羣æŃ£åģļåĪ°
    0.08
    éķ¿å¤§
    0.08
    Activations Density 0.222%

    No Known Activations