© 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. 51517
    Prev
    Next
    INDEX
    Explanations

    `if-else` structure

    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
    ä¹Łæĺ¯å¦ĤæѤ
    -0.13
    æģ¨ä¸įå¾Ĺ
    -0.12
    èģĶç³»æĪij们
    -0.10
    erd
    -0.10
    -0.09
    çīŁ
    -0.09
    åĴĮæĬĢæľ¯
    -0.09
     nutshell
    -0.09
    éĿŀ常好çļĦ
    -0.09
    ocom
    -0.08
    POSITIVE LOGITS
     ê·¸ë¦¬ê³ł
    0.09
    ä¼´
    0.09
    çģµæĦŁ
    0.08
    ãģĿãģĹãģ¦
    0.08
    à¸Ļà¸Ńà¸ģ
    0.08
    -plus
    0.08
    èĢĮå·²
    0.08
     cioè
    0.08
    ä¸įåĥı
    0.08
     Sanity
    0.07
    Activations Density 1.235%

    No Known Activations