© 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. 16594
    Prev
    Next
    INDEX
    Explanations

    download a case study

    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
    å¯Ħ
    -0.10
    æİ°
    -0.09
    身边çļĦ
    -0.09
    ALLOC
    -0.09
    /controllers
    -0.09
     pand
    -0.09
    åĴ±
    -0.09
    çĻ£
    -0.09
     Commons
    -0.09
    .ACCESS
    -0.09
    POSITIVE LOGITS
    éĢīæĭ©äºĨ
    0.10
    çĶ¨äºĨ
    0.10
    该éĻ¢
    0.10
    éģĩåĪ°äºĨ
    0.10
    éĩĩçĶ¨äºĨ
    0.09
    该åħ¬åı¸
    0.09
    å½ĵåľ°æĶ¿åºľ
    0.09
    ä¸Ģå¹´å¤ļ
    0.09
    å¾ĹçĽĬ
    0.09
     Www
    0.09
    Activations Density 0.177%

    No Known Activations