© 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. 26284
    Prev
    Next
    INDEX
    Explanations

    currently, now, always, still

    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
    éĥľ
    -0.10
    管
    -0.09
    ÐĿÐķ
    -0.08
    æİĴéĺŁ
    -0.08
    heimer
    -0.08
    thal
    -0.08
    raphics
    -0.08
    äºĶåħŃ
    -0.08
    èĢĮè¿Ļ
    -0.08
    åģ¥åº·çļĦ
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.10
     Peterson
    0.09
    ä¸Ģ个
    0.09
    æĺ¯ä¸ª
    0.09
    ä¸Ģ个éĩįè¦ģ
    0.08
     внимание
    0.08
    家ä¼Ļ
    0.08
    deer
    0.08
    oS
    0.08
    åĬłçĽĸ
    0.08
    Activations Density 0.041%

    No Known Activations