© 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. 1685
    Prev
    Next
    INDEX
    Explanations

    funding, delivery, misuse, assist, models

    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
    æĬ½åĩº
    -0.12
    æĺ¯ä¸Ģ家
    -0.10
    ç½¢
    -0.09
    æĺ¯éĿŀ
    -0.09
    eel
    -0.09
     SVC
    -0.09
    .wp
    -0.09
    Aaron
    -0.09
    ä¼ģä¸ļæĸĩåĮĸ
    -0.09
    çĤ®
    -0.09
    POSITIVE LOGITS
    æĴ¥
    0.09
     heter
    0.09
    åºķå±Ĥ
    0.09
    æĭ¨
    0.09
    éĩįå¡ij
    0.08
     calam
    0.08
    éĢģæĸĻ
    0.08
    oin
    0.08
    å±±æĿij
    0.08
    ç°ĭ
    0.08
    Activations Density 0.061%

    No Known Activations