© 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. 7863
    Prev
    Next
    INDEX
    Explanations

    vitamin E supplementation

    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
     Lanc
    -0.09
    æĬĽ
    -0.09
    åį®
    -0.09
    æĸ°æł¼å±Ģ
    -0.08
    .rpc
    -0.08
    åĩ«
    -0.08
    rief
    -0.08
    ãģĶ
    -0.08
    éĢıæĺİ
    -0.08
    éĤ¾
    -0.08
    POSITIVE LOGITS
    åѦä¼ļäºĨ
    0.09
    éĺı
    0.09
    ä»£è¡¨åĽ¢
    0.09
    ä¸Ģå¦Ĥ
    0.09
    è¾½
    0.09
    代表
    0.09
    å®ŀåľ°
    0.08
    æŃ¥æŃ¥
    0.08
    æĭ¿äºĨ
    0.08
     Vox
    0.08
    Activations Density 0.028%

    No Known Activations