© 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. 30369
    Prev
    Next
    INDEX
    Explanations

    design pattern and architecture

    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
    åİ¥
    -0.10
    èIJ¥åķĨçݯå¢ĥ
    -0.10
    åĪĽæĸ°èĥ½åĬĽ
    -0.09
    ä¿®åīª
    -0.09
    apel
    -0.09
    _compat
    -0.09
     cher
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.09
    宣
    -0.09
    ä»»ä½ķå½¢å¼ı
    -0.08
    POSITIVE LOGITS
    æŀ¶æŀĦ
    0.10
     пÑĢоÑģ
    0.10
     architectural
    0.09
     Vog
    0.09
     pattern
    0.09
    pattern
    0.09
     trúc
    0.09
    ä¸ī级
    0.09
    patterns
    0.09
    åĪĨ离
    0.09
    Activations Density 0.176%

    No Known Activations