© 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. 866
    Prev
    Next
    INDEX
    Explanations

    Open sourced

    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
     ÑħоÑĤÑĮ
    -0.09
    严èĤĥ
    -0.09
    裸
    -0.09
    fts
    -0.09
    à¥į
    -0.09
    /her
    -0.09
    çĤ¹æ»´
    -0.09
    祼
    -0.08
    äºĪ
    -0.08
    GLE
    -0.08
    POSITIVE LOGITS
    awi
    0.10
    çĭ¬è§Ĵ
    0.09
    ä¹Łä¸įæĥ³
    0.08
    å¤©åĽ½
    0.08
    åľ¨æĦı
    0.08
     Pu
    0.08
    ä¸ĢåŃĹ
    0.08
    æŁģ
    0.08
    Pu
    0.08
    åĩŃè¯ģ
    0.08
    Activations Density 0.071%

    No Known Activations