© 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. 8657
    Prev
    Next
    INDEX
    Explanations

    exposure to conditions or treatments

    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
    é«Ģ
    -0.10
    æ¼ı
    -0.09
    /misc
    -0.09
    å°ĺ
    -0.09
    ä¼¥
    -0.08
     miscar
    -0.08
    ì¢Ģ
    -0.08
    误
    -0.08
    rium
    -0.08
    åĴĦ
    -0.08
    POSITIVE LOGITS
    使åħ¶
    0.10
    æļ´éľ²
    0.10
    conditions
    0.10
    ä¸įåĪ°ä½į
    0.09
     exposure
    0.09
    çŃīåĽłç´ł
    0.09
    æĿ¡ä»¶ä¸ĭ
    0.09
     followed
    0.09
     CONDITIONS
    0.09
    使å¾Ĺ
    0.09
    Activations Density 1.294%

    No Known Activations