© 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. 6117
    Prev
    Next
    INDEX
    Explanations

    Trans-African, Trans-Canada, transmembrane energy

    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
    amat
    -0.11
    è¿Ń
    -0.09
    ores
    -0.09
    æĪİ
    -0.09
    主æŨ
    -0.09
    ä¸įçĶ±
    -0.09
    à¹ĥà¸Ī
    -0.08
    éĺĩ
    -0.08
    oom
    -0.08
    ilst
    -0.08
    POSITIVE LOGITS
    åĴĮåľ°åĮº
    0.14
    é¼İ
    0.10
    èĢĮæĿ¥
    0.10
    纵
    0.09
    太å°ij
    0.08
    ç¼ĿéļĻ
    0.08
    è¯ģåĪ¸æĬķèµĦ
    0.08
     tiá»ĥu
    0.08
    æĶ¯æĮģåĬĽåº¦
    0.08
    éĴİ
    0.08
    Activations Density 0.156%

    No Known Activations