© 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. 8582
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, and units

    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
    подоб
    -0.10
    GER
    -0.09
    æ¯ķç«Ł
    -0.09
    æĪĸå°Ĩ
    -0.08
    asm
    -0.08
    OrDefault
    -0.08
    ger
    -0.08
     ÐĴедÑĮ
    -0.08
    WhatsApp
    -0.08
    åĬŀæ³ķ
    -0.08
    POSITIVE LOGITS
    éĺ²çģ«
    0.09
    ãģķãģ¦
    0.09
    缸åIJĮçļĦ
    0.09
    åIJĮæł·çļĦ
    0.09
    åľ¨åIJĮä¸Ģ
    0.08
    ãģ¡ãĤĩãģĨãģ©
    0.08
    æį®æѤ
    0.08
    å¿ĺäºĨ
    0.08
    å¦Ĥä½ķåİ»
    0.08
    _LOADED
    0.08
    Activations Density 1.974%

    No Known Activations