© 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. 47474
    Prev
    Next
    INDEX
    Explanations

    best-selling author or item

    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
    æĸ°åŁİ
    -0.08
     Ñģобой
    -0.08
    imax
    -0.08
    èĥ¡åŃIJ
    -0.08
    Bookmark
    -0.08
    éķ¿åŁİ
    -0.08
    çģ¾éļ¾
    -0.07
    å²ģ以ä¸ĭ
    -0.07
    ESA
    -0.07
     amo
    -0.07
    POSITIVE LOGITS
    ething
    0.10
    æīĪ
    0.10
    æ¤Ł
    0.10
    å¹³æŶ
    0.10
    æ··åĩĿ
    0.09
    褴
    0.09
    æįº
    0.09
    odu
    0.09
    anax
    0.09
    å´ĸ
    0.09
    Activations Density 0.002%

    No Known Activations