© 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. 24159
    Prev
    Next
    INDEX
    Explanations

    numbers and sizes

    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
    æŁı
    -0.10
    åĻ±
    -0.10
    _CLI
    -0.09
    tá
    -0.09
    éļıæīĭ
    -0.08
    éĶĢæ¯ģ
    -0.08
    èĩŃ
    -0.08
    åĶ
    -0.08
    MES
    -0.08
    æĪ´ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æѤç§į
    0.09
    æľĢéķ¿
    0.09
    饱满
    0.09
    é«ĺç§ijæĬĢ
    0.09
    ãģĦãĤīãģ£ãģĹãĤĥ
    0.08
    è¦ģåĿļæĮģ
    0.08
    ä¸ŃåĽ½çī¹èī²
    0.08
    åºķ
    0.08
    åħ¬è®¤çļĦ
    0.08
    åıijæĮ¥äºĨ
    0.08
    Activations Density 0.137%

    No Known Activations