© 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. 19073
    Prev
    Next
    INDEX
    Explanations

    festival and celebrations

    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
    æĭįæĭį
    -0.09
    .tap
    -0.09
    å¾Ĥ
    -0.09
    è´¯éĢļ
    -0.09
    åIJ¬è¯¾
    -0.09
    è¿Ļ个æĹ¶ä»£
    -0.09
     emb
    -0.09
    ãĤ«ãĥ¡
    -0.09
    æĬļ
    -0.09
    æĭ¾
    -0.09
    POSITIVE LOGITS
    彩
    0.14
     carnival
    0.11
    æ¯ıå¹´
    0.11
    æ¯ıå¹´éĥ½
    0.11
    åIJĨ
    0.10
    ä¸Ģå¹´ä¸Ģ度
    0.10
     annual
    0.10
    éĢīå®ļ
    0.09
    èµĽ
    0.09
    _EVENTS
    0.09
    Activations Density 0.146%

    No Known Activations