© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    ckeditor, editor, tinymce

    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
    å¼ĢåıijèĢħ
    -0.10
    è¹ļ
    -0.10
    ળ
    -0.10
    æĹłèģĬ
    -0.09
    æ·Į
    -0.09
     circulation
    -0.09
    æį§
    -0.09
    èĦIJ
    -0.09
    åīįè¡Į
    -0.09
    åIJįçīĮ
    -0.09
    POSITIVE LOGITS
     editor
    0.10
     editorial
    0.10
    .cms
    0.10
    -editor
    0.10
    /editor
    0.09
    EDITOR
    0.09
    editor
    0.09
    .Editor
    0.09
    å¯Į
    0.09
    ckeditor
    0.09
    Activations Density 0.191%

    No Known Activations