© 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. 62624
    Prev
    Next
    INDEX
    Explanations

    period

    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
    peat
    -0.10
    åį±
    -0.09
    è¿ĻäºĽéĹ®é¢ĺ
    -0.09
    ÑıÑĤÑĮ
    -0.09
    祸
    -0.08
    æĽĻåħī
    -0.08
    è¾IJ
    -0.08
    ä¸Ģåıª
    -0.08
    å·©
    -0.08
    åĿıäºĨ
    -0.08
    POSITIVE LOGITS
    æķ´ä¸ª
    0.10
     whole
    0.09
    æķ´å¤©
    0.09
    æīĢæľī人
    0.09
    æļĤæŶ
    0.09
    åį¡éĢļ
    0.09
    æķ´ä¸ªäºº
    0.09
    æĶ¸
    0.08
    .setEditable
    0.08
     period
    0.08
    Activations Density 0.054%

    No Known Activations