© 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. 29766
    Prev
    Next
    INDEX
    Explanations

    offers and employment contracts

    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
    çĻ½éĽª
    -0.10
    ahr
    -0.09
    9
    -0.09
    olumes
    -0.09
     imagination
    -0.08
    åī§ä¸Ń
    -0.08
    å¼
    -0.08
     Cham
    -0.08
    èĩªåľ¨
    -0.08
    èįIJ
    -0.08
    POSITIVE LOGITS
    åĬ¿åĬĽ
    0.10
    纷纷
    0.10
    åĭ¢
    0.10
    åIJĦæĸ¹
    0.09
    æľīæĽ´å¥½çļĦ
    0.09
    车ä¼ģ
    0.09
    fel
    0.09
    åģļäºĭ
    0.09
    Draft
    0.09
    æĽ´å¥½çļĦ
    0.09
    Activations Density 0.040%

    No Known Activations