© 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. 789
    Prev
    Next
    INDEX
    Explanations

    young animals and their development

    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
    çĤ¹çĩĥ
    -0.09
     Coil
    -0.09
    ä¹ĭç¾İ
    -0.09
     Strike
    -0.08
    æĭĽçīĮ
    -0.08
    大éŨ
    -0.08
    éĴĬ
    -0.08
    平常
    -0.08
    ç»ĺ
    -0.08
    æħ¢æĢ§
    -0.08
    POSITIVE LOGITS
    æĩµ
    0.11
    åIJĮæľŁ
    0.10
    ç¨ļ
    0.10
    born
    0.10
    ä¸ĢåĪ»
    0.09
    -parent
    0.09
    åĪļåĪļ
    0.09
    ä¸Ģ天
    0.09
    åłĤ
    0.09
    ä»Ķ
    0.09
    Activations Density 0.099%

    No Known Activations