© 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. 17938
    Prev
    Next
    INDEX
    Explanations

    take over, winning, gained

    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
    æĸ½å±ķ
    -0.09
    è¿Ļ对äºİ
    -0.08
    åĽ¾æĸĩ
    -0.08
    entr
    -0.08
     Mighty
    -0.08
    墩
    -0.08
    æľºåĬ¨
    -0.08
    favor
    -0.08
     Curt
    -0.08
    ascript
    -0.08
    POSITIVE LOGITS
    缣
    0.10
    讲课
    0.09
    urator
    0.09
    书éĿ¢
    0.09
    oulos
    0.09
    å°±ä¸įä¼ļ
    0.09
    بØŃØ«
    0.09
    habit
    0.09
    æĭĮ
    0.09
    裨
    0.08
    Activations Density 0.036%

    No Known Activations