© 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. 36004
    Prev
    Next
    INDEX
    Explanations

    serious or critical injuries/illness

    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
    龸éģĵ
    -0.09
     далÑĮ
    -0.09
    ÙĦØ©
    -0.09
    åĵģå°Ŀ
    -0.08
    å¦ĤæĦı
    -0.08
    ocks
    -0.08
    å¢ŀ
    -0.08
    lb
    -0.08
    sock
    -0.08
    FFFFFF
    -0.08
    POSITIVE LOGITS
     окол
    0.09
    ugar
    0.09
    æµ®åĬ¨
    0.08
    åıĹ
    0.08
    ahn
    0.08
    itor
    0.08
    ä¸Ģåı°
    0.08
    好è¯Ħ
    0.08
    çį
    0.08
     пÑĢоÑĤ
    0.08
    Activations Density 0.018%

    No Known Activations