© 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. 6121
    Prev
    Next
    INDEX
    Explanations

    defended thesis, supervised

    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
    è®´
    -0.09
    认æ¸ħ
    -0.09
    åIJ¸åħ¥
    -0.09
    ç¼ħ
    -0.09
    æĿ¥çļĦ
    -0.09
    äºī龸
    -0.09
    å¼¼
    -0.09
    æįŀ
    -0.08
    åīį线
    -0.08
    ä»Ģä¹Īåľ°æĸ¹
    -0.08
    POSITIVE LOGITS
    çŃĶ辩
    0.15
     thesis
    0.15
     dissertation
    0.15
     Thesis
    0.15
    thesis
    0.15
    论æĸĩ
    0.13
    åѦä½į
    0.12
    æ¯ķä¸ļ
    0.12
    ç¡ķ士
    0.12
     dissert
    0.11
    Activations Density 0.104%

    No Known Activations