© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33218
    Prev
    Next
    INDEX
    Explanations

    increase/decrease

    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
    æ´ĭæ´ĭ
    -0.09
    åĪ³
    -0.08
    ìĦĿ
    -0.08
    æĭ¿èµ·
    -0.08
    æ³Ľ
    -0.07
     ÙĪØ£ÙĨ
    -0.07
    éĹ®éĹ®
    -0.07
     grinder
    -0.07
     ÙħØŃÙħÙĪد
    -0.07
    æķħæĦı
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.11
    åį´
    0.11
    åį»
    0.10
     lẫn
    0.09
    天ä¸ĭ
    0.09
    çģ«çģ¾
    0.09
    以èĩ³äºİ
    0.09
    ÑĤÑĢо
    0.09
    vron
    0.09
    à¸Ľà¸¥à¸²à¸¢
    0.09
    Activations Density 0.218%

    No Known Activations