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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36743
    Prev
    Next
    INDEX
    Explanations

    time now or soon

    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
    çĦī
    -0.10
    -fw
    -0.09
    ä¸ĢåIJį
    -0.09
    æĺ¶
    -0.09
    æģIJ
    -0.09
    çľ¼çľĭ
    -0.09
    æĮģèĤ¡
    -0.08
    精度
    -0.08
    çłģ
    -0.08
    åIJİæĿ¥
    -0.08
    POSITIVE LOGITS
    ç«ĭåĪ»
    0.11
    å°±å¼Ģå§ĭ
    0.10
    ç«ĭåį³
    0.10
     immediate
    0.10
    积èĵĦ
    0.10
    æĿ¥çĶµ
    0.09
    马ä¸Ĭ
    0.09
    åł°
    0.09
     Immediate
    0.09
    _shadow
    0.09
    Activations Density 0.042%

    No Known Activations