© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8974
    Prev
    Next
    INDEX
    Explanations

    saying statements

    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
    æ¯ĭ
    -0.09
    æīĵçĿĢ
    -0.09
    _consts
    -0.09
    Subsystem
    -0.08
    ãĤĮ
    -0.08
    تÙĪج
    -0.08
    æİ¢
    -0.08
    ä¸įæĪIJ
    -0.08
    дÑĥ
    -0.08
    lá
    -0.08
    POSITIVE LOGITS
    绫
    0.09
    dden
    0.09
    éĤ£ä¸Ģ天
    0.09
    缤纷
    0.09
    æĺ¯ä¸ª
    0.09
    æĽĻ
    0.09
    æľīä»»ä½ķ
    0.08
    (dm
    0.08
    åĭī强
    0.08
    ä¸ĭæ²ī
    0.08
    Activations Density 0.009%

    No Known Activations