© 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. 24305
    Prev
    Next
    INDEX
    Explanations

    compliance with regulations

    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
    bows
    -0.10
    åIJ¦
    -0.09
    æŃ¤äºº
    -0.09
    æİ°
    -0.09
    ä¹İ
    -0.09
    å¾ĹçĽĬ
    -0.09
    æİĩ
    -0.09
    iação
    -0.09
    åĨĴ
    -0.08
    åºĨ幸
    -0.08
    POSITIVE LOGITS
    缸åħ³è§Ħå®ļ
    0.10
     requests
    0.10
    æīįæĺ¯çľŁæŃ£
    0.09
     ÑĤÑĢебованиÑı
    0.09
    è´Ŀ壳
    0.09
    æ³ķå¾ĭè§Ħå®ļ
    0.09
    reme
    0.08
    åħļåĴĮåĽ½å®¶
    0.08
    缸åħ³æĶ¿çŃĸ
    0.08
    è§Ħå®ļ
    0.08
    Activations Density 0.028%

    No Known Activations