© 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. 9348
    Prev
    Next
    INDEX
    Explanations

    occupational exposure limits

    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
    诸èijĽ
    -0.10
    鹤
    -0.09
    agog
    -0.09
    unta
    -0.09
    ulta
    -0.09
    就好åĥı
    -0.09
    èĤ¤
    -0.08
    åķ¬
    -0.08
    çīµ
    -0.08
    ä¿Ŀæļĸ
    -0.08
    POSITIVE LOGITS
    æĢ¡
    0.09
    éĩĩ
    0.09
    çŃĸ
    0.09
    容å¿į
    0.09
    æ´¥
    0.09
    IU
    0.09
    æµĵ度
    0.08
    OPS
    0.08
    ç»ĵ论
    0.08
    人ä½ĵ
    0.08
    Activations Density 0.134%

    No Known Activations