© 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. 9331
    Prev
    Next
    INDEX
    Explanations

    cure and healing diseases

    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
    éºĿ
    -0.11
    ðŁįĮ
    -0.10
    çĿĢçľ¼
    -0.09
    楣
    -0.09
    .ArgumentParser
    -0.09
    主å¸Ń
    -0.09
    åħļç»Ħ
    -0.09
    rage
    -0.09
    arge
    -0.09
    dzi
    -0.09
    POSITIVE LOGITS
    çĹ¼
    0.13
     cure
    0.10
    maid
    0.09
    å°ıä¼Ļ
    0.09
    çİĩè¾¾
    0.09
    åĬŀæ³ķ
    0.08
    ä¸įäºĨ
    0.08
    8
    0.08
    رص
    0.08
    ä¸įå¿ĺ
    0.08
    Activations Density 0.035%

    No Known Activations