© 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. 47615
    Prev
    Next
    INDEX
    Explanations

    counting

    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
    ä¸Ģ个å¤ļæľĪ
    -0.08
    æ´¾
    -0.08
    å±ħçĦ¶
    -0.08
    esian
    -0.08
    综åIJĪåĪ©çĶ¨
    -0.07
     bro
    -0.07
    å²±
    -0.07
    VOICE
    -0.07
    bourg
    -0.07
     quarter
    -0.07
    POSITIVE LOGITS
    ä¸Ģå¦Ĥ
    0.11
    æĮ½
    0.10
    计è¾ĥ
    0.10
    åģİ
    0.10
    èĢĮä¸įæĺ¯
    0.10
    以ä¸ĬçļĦ
    0.09
    被æ·ĺæ±°
    0.09
    ä¹ĥèĩ³
    0.09
    æĹłåĬ©
    0.09
    kil
    0.09
    Activations Density 0.271%

    No Known Activations