© 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. 5143
    Prev
    Next
    INDEX
    Explanations

    lead exposure and health effects

    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
    æĨĭ
    -0.09
    æŁIJç§į
    -0.09
    alcon
    -0.09
    åģ¥
    -0.09
    éĢ¼
    -0.08
    èĨĽ
    -0.08
    -flash
    -0.08
    æľ¬æľŁ
    -0.08
     Tac
    -0.08
    èĭį
    -0.08
    POSITIVE LOGITS
    çł´äº§
    0.09
     ÐijеÑģ
    0.09
    澡
    0.09
    ers
    0.08
    ç§ijæķĻ
    0.08
    å°ģ
    0.08
    èĶº
    0.08
    oru
    0.08
    衾
    0.08
    -lines
    0.08
    Activations Density 0.065%

    No Known Activations