© 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. 867
    Prev
    Next
    INDEX
    Explanations

    climate and geographic locations

    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
    äºķ
    -0.09
    è¾İ
    -0.09
    åĶ®
    -0.09
     Türk
    -0.09
    é¢ħ
    -0.09
    åł°
    -0.09
    ê°Ŀ
    -0.08
    æĮİ
    -0.08
    æĪij们认为
    -0.08
    ç¦ģåĮº
    -0.08
    POSITIVE LOGITS
    æ°ĶåĢĻ
    0.17
    æĹ¥çħ§
    0.13
    åĽĽåŃ£
    0.13
    纬
    0.13
    天æ°Ķ
    0.13
     climate
    0.12
     weather
    0.12
     clim
    0.11
    太éĺ³
    0.11
    åĨ¬åŃ£
    0.11
    Activations Density 0.119%

    No Known Activations