© 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. 40094
    Prev
    Next
    INDEX
    Explanations

    God's will, wants, plans

    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
    Not in Any Lists

    No Comments

    Negative Logits
    onet
    -0.10
     Moder
    -0.09
    itals
    -0.09
    StateChanged
    -0.09
    ä¸įåĬ¨
    -0.09
    mans
    -0.09
    æ¥Ķ
    -0.09
    masına
    -0.09
    æĬĺ
    -0.08
    çħ½
    -0.08
    POSITIVE LOGITS
    亿ä¸ĩ
    0.09
    æĪ¾
    0.09
    æŨ
    0.09
    æĦıåĽ¾
    0.08
    éĺ²æĻĴ
    0.08
    errs
    0.08
    _partitions
    0.08
     ple
    0.08
    æĮª
    0.08
    å¨ģ
    0.08
    Activations Density 0.018%

    No Known Activations