© 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. 30932
    Prev
    Next
    INDEX
    Explanations

    book generator

    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
    rab
    -0.09
     mandate
    -0.08
    åĥļ
    -0.08
    éĴ¢ç®¡
    -0.08
    errat
    -0.08
     Mand
    -0.08
     Branch
    -0.07
    æĢĤ
    -0.07
     scand
    -0.07
    æ¨Ĺ
    -0.07
    POSITIVE LOGITS
    äºĨå¤ļå°ij
    0.10
    赤
    0.10
    Corn
    0.09
    çī¹æľīçļĦ
    0.09
    åij¨åĽ´çļĦ
    0.09
    çļĦæĸ¹å¼ıæĿ¥
    0.09
    æµij身
    0.08
    ãĤĪ
    0.08
    iesz
    0.08
    åĴĮä»ĸçļĦ
    0.08
    Activations Density 0.268%

    No Known Activations