© 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. 55020
    Prev
    Next
    INDEX
    Explanations

    experiencing medical conditions

    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
    æijĺ
    -0.10
    ÑģкоÑĢ
    -0.09
    æĪĴæĮĩ
    -0.09
    ળ
    -0.09
    åģľçķĻåľ¨
    -0.09
    æ´»ä¸ĭåİ»
    -0.09
    俶
    -0.09
    /licenses
    -0.09
    town
    -0.08
    ylene
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮç¨ĭ度
    0.10
    轻微
    0.09
    çļĦæĥħåĨµ
    0.09
     nearest
    0.08
    çļĦåıĺåĮĸ
    0.08
    åīįæīĢæľª
    0.08
    ate
    0.08
    ä¸ĩåĪĨ
    0.08
    ä¹IJ趣
    0.08
    dra
    0.08
    Activations Density 0.033%

    No Known Activations