© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17970
    Prev
    Next
    INDEX
    Explanations

    organ transplantation procedures

    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®£ä¼łæ´»åĬ¨
    -0.11
    åħ¨éĿ¢èIJ½å®ŀ
    -0.11
    好äºĭ
    -0.10
    å¤įå·¥
    -0.10
    第ä¸Ģ次
    -0.10
    çĽį
    -0.09
    èĢķ
    -0.09
    _nl
    -0.09
    å¤įå·¥å¤į产
    -0.09
    èIJ½å®ŀ
    -0.09
    POSITIVE LOGITS
     serial
    0.08
    寸
    0.08
    rose
    0.08
    缸è§ģ
    0.08
    listing
    0.08
    满满çļĦ
    0.08
    ATTR
    0.08
     обо
    0.08
    éľī
    0.08
    åķĨä¸ļåĮĸ
    0.08
    Activations Density 0.349%

    No Known Activations