© 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. 24079
    Prev
    Next
    INDEX
    Explanations

    advertising displays

    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
    æĦı大
    -0.09
    ABCDEFGHI
    -0.09
    ç½ijéĢļ
    -0.09
    éĹ²
    -0.08
    setLabel
    -0.08
    ä»ĩ
    -0.08
     Glow
    -0.08
    åħ¨å¥Ĺ
    -0.08
    å¾®éĩıåħĥç´ł
    -0.08
    nek
    -0.08
    POSITIVE LOGITS
    æĦļ
    0.10
    åħµé©¬
    0.09
    èµŀæĪIJ
    0.09
    æĶ¾è¿ĩ
    0.09
    å¥ı
    0.08
    åħļæĶ¿
    0.08
    /banner
    0.08
    assen
    0.08
    æĮģæľī人
    0.08
    è§ģæķĪ
    0.08
    Activations Density 0.007%

    No Known Activations