© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    COVID-19 pandemic

    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
    ç¨ļ
    -0.09
    å²ģ以ä¸ĭ
    -0.09
    éĢ
    -0.09
    çĤ¯
    -0.09
    渥
    -0.08
    åIJĦéĥ¨éŨ
    -0.08
    èĥľ
    -0.08
    æĿijéĩĮ
    -0.08
    建设çĶ¨åľ°
    -0.08
    为äºĨ让
    -0.08
    POSITIVE LOGITS
    çĸ«æĥħ
    0.18
    æĸ°åŀĭåĨłçĬ¶
    0.16
    汶å·Ŀ
    0.16
    çĸ«æĥħæľŁéĹ´
    0.16
    éĩijèŀįåį±æľº
    0.15
    æĸ°åĨłçĸ«æĥħ
    0.15
     pandemic
    0.14
     COVID
    0.14
     coronavirus
    0.14
    æĸ°åĨłçĹħæ¯Ĵ
    0.14
    Activations Density 0.549%

    No Known Activations