© 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. 58817
    Prev
    Next
    INDEX
    Explanations

    previous years and editions

    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
    æķ´å¤©
    -0.10
    éļĻ
    -0.09
    ioni
    -0.09
    å°½æĹ©
    -0.08
    æĹ¥æĬ¥
    -0.08
    clo
    -0.08
    ä¸ŃåĽ½æĶ¿åºľ
    -0.08
     clo
    -0.08
    åģļçĶŁæĦı
    -0.08
    á¹£
    -0.08
    POSITIVE LOGITS
    æ¯ıå¹´éĥ½
    0.24
    æ¯ıå¹´
    0.21
    å¾Ģå¹´
    0.21
    éĢIJå¹´
    0.16
    ä¸Ģå¹´ä¸Ģ度
    0.15
    æ¯ı次éĥ½
    0.15
     annually
    0.14
     annual
    0.14
    æ¯ı次
    0.14
    ä»Ĭå¹´
    0.13
    Activations Density 0.164%

    No Known Activations