© 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. 8298
    Prev
    Next
    INDEX
    Explanations

    quantities, currency, or rates

    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
    omap
    -0.11
    åģļçļĦ
    -0.10
    çĴĭ
    -0.09
    ocity
    -0.09
    Ỽ
    -0.09
     satur
    -0.09
    æĬĬæı¡
    -0.09
    ç²ķ
    -0.09
    owe
    -0.08
    quine
    -0.08
    POSITIVE LOGITS
    ä¸įå¿ħè¦ģçļĦ
    0.10
    å¢ŀåĬłäºĨ
    0.10
    ä½ĵçİ°åľ¨
    0.10
    æ·»
    0.10
    é¢Ŀå¤ĸ
    0.09
    è¿ĺä¸įå¤Ł
    0.09
    ä¸įå°ıçļĦ
    0.09
     Marvin
    0.09
    个çĻ¾åĪĨçĤ¹
    0.09
    该éĻ¢
    0.09
    Activations Density 0.113%

    No Known Activations