© 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. 9239
    Prev
    Next
    INDEX
    Explanations

    company that owns

    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
    çĪ±äºº
    -0.09
     ÄijÃłn
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    ãĥ£
    -0.08
    æħİ
    -0.08
    模èĮĥ
    -0.08
    [--
    -0.08
     Äijây
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
    è¿Ļå°±æĺ¯
    -0.08
    POSITIVE LOGITS
    ä¸ŃåİŁ
    0.09
    å¤ļå±Ĥ次
    0.09
    è°ĥçļ®
    0.08
    ViewItem
    0.08
    已达
    0.08
    until
    0.08
    çļĦçŁ¥è¯Ĩ
    0.08
    pto
    0.08
     non
    0.08
    è§ľ
    0.08
    Activations Density 0.089%

    No Known Activations