© 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. 36837
    Prev
    Next
    INDEX
    Explanations

    blood flow obstruction

    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
    arily
    -0.10
    ×Ļק
    -0.09
    è¢į
    -0.08
    ELY
    -0.08
    CESS
    -0.08
    ä¹IJåĽŃ
    -0.08
    _capability
    -0.08
    5
    -0.08
    æĦıä¹īä¸ĬçļĦ
    -0.08
    isky
    -0.08
    POSITIVE LOGITS
    buster
    0.12
    ä½ıäºĨ
    0.10
    ä¸įåłª
    0.10
    busters
    0.10
    ç¯
    0.10
    è§ĨåIJ¬
    0.09
    é¢ĸ
    0.09
    å¾Ĺä½ı
    0.08
    -haired
    0.08
    ä½ı
    0.08
    Activations Density 0.021%

    No Known Activations