© 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. 6207
    Prev
    Next
    INDEX
    Explanations

    research analysis and reporting

    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
    æĵįæݧ
    -0.09
    çݰ代
    -0.08
    èµĶ
    -0.08
    åĺĽ
    -0.08
    rew
    -0.08
    严éĩį
    -0.07
     modern
    -0.07
    å¯ħ
    -0.07
    æģ©
    -0.07
    רק
    -0.07
    POSITIVE LOGITS
     disag
    0.11
    è´²
    0.10
    æŶ髦
    0.09
    æľīçļĦçݩ家
    0.09
    åIJ¸çº³
    0.09
    åij¼åºĶ
    0.08
    EEP
    0.08
    éĽī
    0.08
    ãģ¤ãģª
    0.08
    ä¸ĵ家åѦèĢħ
    0.08
    Activations Density 0.266%

    No Known Activations