© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49332
    Prev
    Next
    INDEX
    Explanations

    occupational exposure to hazards

    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
     unst
    -0.09
    éļĻ
    -0.09
     hacks
    -0.09
    å¤ĩçĶ¨
    -0.09
    ipt
    -0.09
    _patches
    -0.09
     ramp
    -0.09
    ippers
    -0.08
     Times
    -0.08
    ç»ķ
    -0.08
    POSITIVE LOGITS
    èģĮä¸ļ
    0.15
     bụi
    0.11
     occupational
    0.11
    ç²īå°ĺ
    0.11
    塵
    0.11
    èģĮä¸ļéģĵå¾·
    0.10
    èĢ³è¾¹
    0.10
    (Optional
    0.10
    å°ĺ
    0.10
    åĬ³åĬ¨èĢħ
    0.10
    Activations Density 0.364%

    No Known Activations