© 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. 21319
    Prev
    Next
    INDEX
    Explanations

    multitasking and managing complexity

    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
    _VO
    -0.11
    åıĹçĽĬ
    -0.10
    代价
    -0.09
    å¾ĹçĽĬ
    -0.09
    ibrator
    -0.09
    身份è¯ģ
    -0.09
    /cms
    -0.09
    .bundle
    -0.09
    å¾Īæĸ¹ä¾¿
    -0.09
    ÙĬاÙĨ
    -0.09
    POSITIVE LOGITS
    åıĪè¦ģ
    0.18
    è¿ĺè¦ģ
    0.17
    æĹ¢è¦ģ
    0.15
    åĬłä¸Ĭ
    0.13
    ä¸įä»ħè¦ģ
    0.13
    éĤĦè¦ģ
    0.13
     plus
    0.12
    åĨįåĬłä¸Ĭ
    0.12
    è¦ģèĢĥèĻij
    0.12
    è¿ĺå¾Ĺ
    0.12
    Activations Density 0.072%

    No Known Activations