© 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. 7915
    Prev
    Next
    INDEX
    Explanations

    Workers' compensation insurance

    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
    aque
    -0.11
    ohl
    -0.10
     Ops
    -0.09
    å¿ĥè¡Ģ
    -0.09
    atz
    -0.09
    åĸĩåıŃ
    -0.09
    å±ģèĤ¡
    -0.09
    веÑģ
    -0.09
    éĴ¥
    -0.09
    å®ŀåĬĽ
    -0.08
    POSITIVE LOGITS
    工伤
    0.14
    åıĹ伤
    0.14
     injury
    0.11
    Workers
    0.11
     injured
    0.11
    ä¿ĿéĻ©
    0.11
    工人
    0.10
     Workers
    0.10
    伶
    0.10
    ä¿Ŀéļª
    0.10
    Activations Density 0.225%

    No Known Activations