© 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. 53941
    Prev
    Next
    INDEX
    Explanations

    taxpayer money and funding

    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
    åĴĮæĶ¯æĮģ
    -0.09
    .extent
    -0.09
    åŀ£
    -0.09
    åıįæĬĹ
    -0.09
    owy
    -0.09
    æŃ¹
    -0.09
    æĬ¥éħ¬
    -0.09
    éĶ¢
    -0.09
    èĩŃ
    -0.08
    æĿ³
    -0.08
    POSITIVE LOGITS
    arend
    0.12
    alley
    0.09
     اÙĦعرب
    0.09
    åŃIJ女
    0.08
    .cum
    0.08
    èĨĽ
    0.08
     heed
    0.08
    inos
    0.08
    -facing
    0.08
    æĮ¯å¥ĭ
    0.08
    Activations Density 0.009%

    No Known Activations