© 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. 6108
    Prev
    Next
    INDEX
    Explanations

    senior self-care activities

    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
    PEG
    -0.10
    ä¸įæĺİ
    -0.10
    åħ¨ä½ĵåijĺå·¥
    -0.09
    èľĪ
    -0.09
    èħ»
    -0.09
     rio
    -0.09
    é©°
    -0.08
     Remix
    -0.08
    _FOREACH
    -0.08
    æķ´å½¢
    -0.08
    POSITIVE LOGITS
    åģļé¥Ń
    0.12
    家åĬ¡
    0.10
    çħ§æĸĻ
    0.10
    æĸĻçIJĨ
    0.10
    çĽĤ
    0.09
    åľ¨å®¶
    0.09
    èĩªçIJĨ
    0.09
    太太
    0.09
    çĶŁæ´»
    0.09
    åij¨åĽ´çļĦ
    0.09
    Activations Density 0.053%

    No Known Activations