© 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. 11283
    Prev
    Next
    INDEX
    Explanations

    brands and products

    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
    aby
    -0.09
    æĹłèģĬ
    -0.09
    ubby
    -0.09
    太平
    -0.09
    å°ıå§IJå§IJ
    -0.09
    IGIN
    -0.09
    å§ij
    -0.09
    åĩ«
    -0.08
    awah
    -0.08
    BAB
    -0.08
    POSITIVE LOGITS
     мÑı
    0.09
    ç§ijæĬĢèĤ¡ä»½
    0.08
    å¼
    0.08
    é»ijé¾Ļ
    0.08
    åĹħ
    0.08
    å±¥
    0.08
    éĿ´
    0.08
    initialized
    0.08
     вÑģÑİ
    0.08
    趾
    0.08
    Activations Density 0.019%

    No Known Activations