© 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. 35064
    Prev
    Next
    INDEX
    Explanations

    or followed by conjunctions

    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
    è¦ģä¹Ī
    -0.10
    ä¸įä½Ĩ
    -0.09
    ä¹Łæľī
    -0.09
     either
    -0.09
    ä¹Łæľīä¸ĢäºĽ
    -0.09
    ä¸Ģéĥ¨
    -0.09
    ä¸įåİ»
    -0.09
    either
    -0.09
    ä¸įä»ħ
    -0.09
    æĽ´å¤ļçļĦæĺ¯
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.15
    ä¹Łä¸įåı¯èĥ½
    0.14
     necessarily
    0.12
     Ø¥ÙĦا
    0.12
    ä»»ä½ķå½¢å¼ı
    0.11
    éĤ£ä¹Ī容æĺĵ
    0.11
     nor
    0.10
     سÙĪÙī
    0.10
     ×IJ׾×IJ
    0.10
    ä¼ģåĽ¾
    0.09
    Activations Density 0.062%

    No Known Activations