© 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. 11032
    Prev
    Next
    INDEX
    Explanations

    playing or returning to action

    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
     Reyn
    -0.11
    çļĦçĶ»éĿ¢
    -0.10
    æľªæĪIJ
    -0.10
    æĹ©é¤IJ
    -0.09
    å½ķ
    -0.09
    ÑĤели
    -0.09
    人家
    -0.09
    ä¸Ģå¹ķ
    -0.08
    urat
    -0.08
    ạn
    -0.08
    POSITIVE LOGITS
    åıĥåĬł
    0.11
    åıĤåĬł
    0.10
    fully
    0.10
    å¦ĤæľŁ
    0.10
     fully
    0.10
    гаÑĢ
    0.10
    ãĤĴè¿İ
    0.09
    çªŁ
    0.09
    alla
    0.09
    æĹłç¼Ŀ
    0.09
    Activations Density 0.020%

    No Known Activations