© 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. 55728
    Prev
    Next
    INDEX
    Explanations

    annoying, inconvenient, pain, tedious

    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
    å¥ĩ迹
    -0.11
    çijĻ
    -0.09
    å»ĵ
    -0.09
    å¨ĺ
    -0.09
    åŃ©
    -0.09
    çłĶåĪ¤
    -0.08
     Shed
    -0.08
     Tough
    -0.08
    æģº
    -0.08
    craft
    -0.08
    POSITIVE LOGITS
    çĶ¨æĪ·ä½ĵéªĮ
    0.12
    便æį·
    0.11
    让人
    0.10
    ä¸įæĸ¹ä¾¿
    0.10
    便æ°ij
    0.10
    ä½ĵéªĮ
    0.09
    çĥ¦æģ¼
    0.09
    é¢ijé¢ij
    0.09
     inconvenience
    0.09
    ç¢ĵ
    0.09
    Activations Density 0.191%

    No Known Activations