© 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. 24199
    Prev
    Next
    INDEX
    Explanations

    judicial estoppel

    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
    ä¸įç»ı
    -0.09
    äºĭåĬ¡
    -0.08
    ä¹ĭ家
    -0.08
    exus
    -0.08
    ences
    -0.08
    ä¸įåİ»
    -0.08
    çļĦæĿĥåĪ©
    -0.08
    å¿«æĬ¥
    -0.08
     Herman
    -0.08
    çķª
    -0.08
    POSITIVE LOGITS
     Leban
    0.11
    éģ¿
    0.10
    è¿Ń
    0.09
    鼳
    0.09
    Nib
    0.09
    论è¯ģ
    0.08
    rena
    0.08
    ç§ijåѦçłĶ究
    0.08
    çĹĴ
    0.08
    utting
    0.08
    Activations Density 0.092%

    No Known Activations