© 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. 24020
    Prev
    Next
    INDEX
    Explanations

    Kaepernick sparked/neighborhood

    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
    è±¢
    -0.10
    ç´łè´¨æķĻèĤ²
    -0.09
    åľ¨æĦı
    -0.09
    èĶ¼
    -0.09
    èµ·ä¾Ĩ
    -0.09
    çķħ
    -0.09
    ÑĭÑĪ
    -0.09
    rial
    -0.08
    大ä¼ļä¸Ĭ
    -0.08
    .edu
    -0.08
    POSITIVE LOGITS
    好å¤Ħ
    0.09
    åħ¨åŁŁ
    0.08
     GPLv
    0.08
    è¯ĭ
    0.07
     VO
    0.07
    unci
    0.07
    æ²ī
    0.07
    åłĤ
    0.07
    zac
    0.07
    ä¼ļåIJĮ
    0.07
    Activations Density 0.143%

    No Known Activations