© 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. 26046
    Prev
    Next
    INDEX
    Explanations

    future possibilities and decisions

    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
    æĽ¿è¡¥
    -0.09
    å°±åĮ»
    -0.09
    åıĹçĽĬ
    -0.08
    æĥ³äºĨæĥ³
    -0.08
    åīįæıIJ
    -0.08
     Wein
    -0.08
    毫ä¸į
    -0.08
    ÑħоÑĤ
    -0.08
     hal
    -0.08
    äºĨ个
    -0.08
    POSITIVE LOGITS
    æĭŃ
    0.12
    æĸ°çļĦä¸Ģå¹´
    0.11
    èĥ½åIJ¦
    0.11
    ä¸ĩåı°
    0.11
    å¸ĥ
    0.11
    èĥ½æĬĬ
    0.10
    iou
    0.10
    åħĭæľį
    0.10
    åĪ»
    0.10
    æŶéļĶ
    0.10
    Activations Density 0.037%

    No Known Activations