© 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. 30254
    Prev
    Next
    INDEX
    Explanations

    purchasing more

    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
    ä¸İä¼Ĺ
    -0.10
    вÑĪ
    -0.09
     Gong
    -0.09
    æīĢè°ĵ
    -0.09
    inha
    -0.09
    责任
    -0.09
    æĥ³è¿ĩ
    -0.09
    bai
    -0.08
    ição
    -0.08
    æĤī
    -0.08
    POSITIVE LOGITS
     outnumber
    0.13
    è¸Ĭè·ĥ
    0.11
    çļĦæķ°éĩı
    0.11
    æľĢå¤ļçļĦ
    0.11
    è¸
    0.11
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.10
    è¶Ĭå¤ļ
    0.10
    为主ä½ĵ
    0.10
    å¢ŀå¤ļ
    0.10
    人æķ°
    0.10
    Activations Density 0.126%

    No Known Activations