© 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. 24275
    Prev
    Next
    INDEX
    Explanations

    academic degrees (MD, PhD, MS)

    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
    çģ«çĥŃ
    -0.10
    endar
    -0.09
    imals
    -0.09
    éĺŁéķ¿
    -0.09
    ãģĤãģ£ãģ¦
    -0.09
    star
    -0.09
    è´©åįĸ
    -0.09
    tml
    -0.08
    estre
    -0.08
     Shaun
    -0.08
    POSITIVE LOGITS
    æ¯ı次éĥ½
    0.09
     latter
    0.09
    èĢħãģ¯
    0.09
    olle
    0.08
    ors
    0.08
     chap
    0.08
    èĸľ
    0.08
    å¸ĪèĮĥ
    0.08
    æ¯ıä¸Ģ次
    0.08
    åIJĦè¡Į
    0.08
    Activations Density 0.008%

    No Known Activations