© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24227
    Prev
    Next
    INDEX
    Explanations

    res followed by specific suffixes

    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
    Negative Logits
    为äºĨæĽ´å¥½
    -0.10
    å·¥ä½ľä¼ļè®®
    -0.09
    让æĤ¨
    -0.09
    town
    -0.09
    ä¸įæŃ»
    -0.09
     CIM
    -0.09
    éĿŀ常æĺİæĺ¾
    -0.09
    çļĦä¸ĢéĿ¢
    -0.09
    åIJİæİĴ
    -0.09
    ç»ĻæĤ¨
    -0.09
    POSITIVE LOGITS
    /res
    0.14
    -res
    0.10
    erves
    0.10
    (res
    0.09
    é¹ĥ
    0.09
    	res
    0.09
    rés
    0.09
    .RES
    0.09
     res
    0.09
    ponsive
    0.09
    Activations Density 0.032%

    No Known Activations