© 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. 63989
    Prev
    Next
    INDEX
    Explanations

    oversees or oversees

    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
    åĦ¿
    -0.10
    iefs
    -0.09
    ä¸Ŀ毫
    -0.09
    主æĦı
    -0.09
    çĪ¶åŃIJ
    -0.09
    æºIJæ³ī
    -0.08
    ä½ĵä¼ļ
    -0.08
    è¿ĩå¹´
    -0.08
    ization
    -0.08
    .sap
    -0.08
    POSITIVE LOGITS
     SimpleName
    0.09
    acre
    0.09
    è¹
    0.09
    ðŁı»
    0.09
    olds
    0.08
    ол
    0.08
    yer
    0.08
    imb
    0.08
    umps
    0.08
    颦
    0.08
    Activations Density 0.005%

    No Known Activations