© 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. 22961
    Prev
    Next
    INDEX
    Explanations

    individualized medicine and oncology

    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
    åIJįèªī
    -0.09
     Dut
    -0.08
    满满çļĦ
    -0.08
     Simple
    -0.08
    èĥľä»»
    -0.08
     ing
    -0.08
    æ´¸
    -0.08
    æĸĻ
    -0.07
     Zam
    -0.07
     Ron
    -0.07
    POSITIVE LOGITS
    个ä½ĵ
    0.28
    个æĢ§åĮĸ
    0.24
    个人
    0.22
    个æĢ§
    0.22
     individual
    0.20
    individual
    0.20
    åĴĮ个人
    0.20
    åĢĭ人
    0.19
     individ
    0.19
     ê°ľìĿ¸
    0.18
    Activations Density 0.287%

    No Known Activations