© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4272
    Prev
    Next
    INDEX
    Explanations

    stick with

    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
    verb
    -0.09
    è§ĩ
    -0.09
    æĶ¶æĭ¾
    -0.08
    å¥ĸåѦéĩij
    -0.08
     stakes
    -0.08
    åģķ
    -0.08
    亮
    -0.08
    liced
    -0.08
    è¨Ģ论
    -0.08
    otal
    -0.08
    POSITIVE LOGITS
    人éĹ´
    0.10
    å¤§åľ°
    0.10
    å¦ĤæĦı
    0.09
    çļĩä¸Ĭ
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
    åĽłä¸ºä»ĸ们
    0.09
     Ced
    0.09
    yal
    0.09
    å¤Ł
    0.08
    æĥ©ç½ļ
    0.08
    Activations Density 0.006%

    No Known Activations