© 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. 60833
    Prev
    Next
    INDEX
    Explanations

    seat selection and fees

    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
    çį¾
    -0.11
    æ¢ĵ
    -0.10
    å¼Ģåĩº
    -0.10
    说å®ŀ
    -0.10
    ä¾¿å®ľ
    -0.09
    è°ĥ度
    -0.09
    ä¹Łä¸įæķ¢
    -0.09
     Stone
    -0.09
    延å®ī
    -0.09
    çĭ¼
    -0.09
    POSITIVE LOGITS
    座ä½į
    0.10
    票价
    0.09
    å¤į
    0.09
     билеÑĤ
    0.09
     chân
    0.09
    umba
    0.09
     Cabin
    0.09
    åħ³æĢĢ
    0.09
    é«»
    0.09
    ç²¾åĵģ
    0.08
    Activations Density 0.063%

    No Known Activations