© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22282
    Prev
    Next
    INDEX
    Explanations

    text corpus data file

    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
    имв
    -0.10
    åѤçĭ¬
    -0.09
    ategorized
    -0.09
    æĭīæĸ¯
    -0.09
    egrity
    -0.09
    _primitive
    -0.09
    ä»İä¸ļ
    -0.09
    åı¯æĢľ
    -0.09
    形象
    -0.09
    å¯Ĥå¯ŀ
    -0.09
    POSITIVE LOGITS
     Bain
    0.11
     Hav
    0.09
    é¢ĦæĸĻ
    0.08
    è¿Ļ段
    0.08
    åĽŃåĮº
    0.08
     Shed
    0.08
    å¥łåŁº
    0.08
     shed
    0.08
    ä¸Ģ段
    0.08
    å¤ļç§įå½¢å¼ı
    0.08
    Activations Density 0.070%

    No Known Activations