© 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. 22833
    Prev
    Next
    INDEX
    Explanations

    and their

    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
    æīĥ
    -0.09
    ä¸įè´Ł
    -0.08
    æįī
    -0.08
    ä¹Łæĺ¯éĿŀ常
    -0.08
    æİ£
    -0.08
    æĺŁåħī
    -0.08
    ãģ«åħ¥ãģ£ãģ¦
    -0.08
    æĪĸèĢħ说
    -0.08
    å®ŀåľ¨
    -0.08
    åĴĮ个人
    -0.08
    POSITIVE LOGITS
    åį³ä¾¿æĺ¯
    0.11
    ä¸ĢåĪĩéĥ½
    0.10
    åį³ä¾¿
    0.09
     there
    0.09
    æľīè¶³å¤ŁçļĦ
    0.09
    there
    0.09
    京津
    0.09
    è±ģ
    0.08
    å°±è¿ŀ
    0.08
    æľīäºĽ
    0.08
    Activations Density 0.169%

    No Known Activations