© 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. 51529
    Prev
    Next
    INDEX
    Explanations

    drug-drug interactions

    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
    议论
    -0.10
     Minds
    -0.09
    strain
    -0.09
    æĭ¥æĬ¤
    -0.09
    ControlEvents
    -0.09
    å¿ĥçIJĨ
    -0.09
    ç¬ij声
    -0.09
    以å¤ĸ
    -0.09
    æĭ¥
    -0.08
    çķ¸å½¢
    -0.08
    POSITIVE LOGITS
    åħ¼å®¹
    0.13
    ä¼ļå½±åĵį
    0.11
     compatibility
    0.11
    缸äºĴ
    0.11
     compat
    0.10
    çļĦå½±åĵį
    0.10
    .compat
    0.10
    compat
    0.10
    compatible
    0.09
     Compatibility
    0.09
    Activations Density 0.228%

    No Known Activations