© 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. 20596
    Prev
    Next
    INDEX
    Explanations

    physical discomfort and ailments

    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
    踪
    -0.10
    è¹Ħ
    -0.10
    æīĵ交
    -0.09
    åĨ¤
    -0.09
    尾巴
    -0.08
    stalk
    -0.08
    pons
    -0.08
    æľĽçĿĢ
    -0.08
    代çIJĨ
    -0.08
    æ¯ıæľĪ
    -0.08
    POSITIVE LOGITS
    绿èī²éĢļéģĵ
    0.11
    赶紧
    0.10
    åĿIJä¸ĭ
    0.10
    çľ¼éķľ
    0.10
    ä¼ijæģ¯
    0.10
    æĢ¥éľĢ
    0.10
    ä»Ģä¹Īåľ°æĸ¹
    0.10
    æī¶
    0.10
     Nap
    0.10
     resting
    0.09
    Activations Density 0.036%

    No Known Activations