© 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. 23210
    Prev
    Next
    INDEX
    Explanations

    take a look at

    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
    å¹¿æ³ĽçļĦ
    -0.11
    ä¸¥æł¼çļĦ
    -0.10
    åħ´è¶£
    -0.10
    æĺİæľĹ
    -0.09
    ä½ķå¤Ħ
    -0.09
    ä¸ĢèĦļ
    -0.09
    avern
    -0.09
    igan
    -0.09
    ä¸įåģľçļĦ
    -0.08
    ä¸Ģå¼Ģå§ĭå°±
    -0.08
    POSITIVE LOGITS
    æīĭä¸ŃçļĦ
    0.10
     how
    0.09
    ä»Ģä¹Īæĺ¯
    0.09
    è¿Ļ对
    0.09
    éļ¾å¾Ĺ
    0.09
    æĪij们åºĶ该
    0.08
     what
    0.08
    ãĤ«ãĥ«
    0.08
    æĽ´å¤ļ精彩
    0.08
    ä»Ģä¹Īåı«
    0.08
    Activations Density 0.040%

    No Known Activations