© 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. 52432
    Prev
    Next
    INDEX
    Explanations

    began performing, learned guitar, attended, acted, working, playing

    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
    åįķ身
    -0.08
     bikini
    -0.08
     Parenthood
    -0.08
    æĥ³æĥ³
    -0.08
    åįĥåı¤
    -0.08
    ä¸ĵ人
    -0.08
    为ä¹ĭ
    -0.08
    奥æŀĹ
    -0.08
    缴å±ŀ
    -0.08
    ä¸ļæĢģ
    -0.08
    POSITIVE LOGITS
    ä»İå°ıå°±
    0.14
    å°ıæŶåĢĻ
    0.11
    _$_
    0.10
    天èµĭ
    0.10
    åIJ¯èĴĻ
    0.10
    æ¶Ĥ
    0.10
    åľ¨åŃ¦æł¡
    0.10
    uze
    0.09
    ä»İå°ı
    0.09
    çľĭçĶµè§Ĩ
    0.09
    Activations Density 0.245%

    No Known Activations