© 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. 20113
    Prev
    Next
    INDEX
    Explanations

    distance, dog, stock, com

    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
    vod
    -0.10
    forces
    -0.10
    ehr
    -0.09
    å¥
    -0.09
    ãĥIJãĥ³
    -0.09
    aza
    -0.09
    åĨķ
    -0.09
    æİĴæĸ¥
    -0.08
    å¤ļç§įå½¢å¼ı
    -0.08
    åľ¨æĪijçļĦ
    -0.08
    POSITIVE LOGITS
    æĿĤå¿Ĺ社
    0.12
    æ·Į
    0.09
    Ltd
    0.09
    æĸĩåĮĸä¼łåªĴ
    0.09
    æįī
    0.09
    ftware
    0.09
    æĺ¯ä¸Ģ座
    0.08
    天é¹ħ
    0.08
    åįļæĸĩ
    0.08
    客
    0.08
    Activations Density 0.163%

    No Known Activations