© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52759
    Prev
    Next
    INDEX
    Explanations

    selected pediatric centers

    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
    Configuration
    -0.09
    人为
    -0.09
    å°ī
    -0.08
     беÑģплаÑĤно
    -0.08
    åĽĽçº§
    -0.08
    åĪĨ级
    -0.08
    ilenames
    -0.08
     Dirt
    -0.08
    åĤ»
    -0.08
    æĢĿç»´
    -0.08
    POSITIVE LOGITS
    é¢ĨåŁŁ
    0.21
    é¢ĨåŁŁçļĦ
    0.20
    éłĺåŁŁ
    0.17
    éĩįçĤ¹é¢ĨåŁŁ
    0.17
     lĩnh
    0.16
    ä¸ĢéŨ
    0.15
    ç§ij缮
    0.15
    é¢ĺæĿIJ
    0.15
     domains
    0.14
    åĵģç±»
    0.12
    Activations Density 0.458%

    No Known Activations