© 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. 22217
    Prev
    Next
    INDEX
    Explanations

    taxpayer-subsidized healthcare plans

    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
    åĨ¶
    -0.09
    æ·ĺ
    -0.09
    享èªī
    -0.08
    常è§Ħ
    -0.08
    赦
    -0.08
    æ´¾åĩºæīĢ
    -0.08
    artz
    -0.08
    泯
    -0.08
    obe
    -0.08
    åĪĹ为
    -0.08
    POSITIVE LOGITS
    åĮ»çĸĹä¿ĿéĻ©
    0.13
    åĮ»ä¿Ŀ
    0.13
    åĮ»çĸĹæľįåĬ¡
    0.11
    åıĤä¿Ŀ
    0.10
    åħ¬ç«ĭåĮ»éĻ¢
    0.10
     Healthcare
    0.10
     healthcare
    0.10
    .fhir
    0.10
     Marketplace
    0.10
    Med
    0.10
    Activations Density 0.099%

    No Known Activations