© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52678
    Prev
    Next
    INDEX
    Explanations

    school technology

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Borders
    -0.11
     Shard
    -0.09
     Universities
    -0.09
     universities
    -0.09
    大åѦçĶŁ
    -0.08
    çī¢
    -0.08
    é«ĺçŃīæķĻèĤ²
    -0.08
     Border
    -0.08
    çIJĨå·¥
    -0.08
    æľīç§į
    -0.08
    POSITIVE LOGITS
    æł¡
    0.12
    æł¡éķ¿
    0.11
    åī¯æł¡éķ¿
    0.11
    æĶ¾åѦ
    0.11
    è¿Ļ两年
    0.11
     school
    0.11
    åŃ¦æł¡
    0.11
    å¼łè´´
    0.10
    åŃ¦æł¡çļĦ
    0.10
    沤
    0.10
    Activations Density 0.163%

    No Known Activations