© 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. 36848
    Prev
    Next
    INDEX
    Explanations

    brilliant light and glare

    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
    	Serial
    -0.09
    å½ĺ
    -0.08
    iqu
    -0.08
    oxy
    -0.08
    åİ¢
    -0.08
    çİĩ为
    -0.08
    é£İåij³
    -0.08
    locate
    -0.08
    æĭĸæ¬ł
    -0.08
    ertext
    -0.08
    POSITIVE LOGITS
    èĢĢçľ¼
    0.16
    äº®çľ¼
    0.11
    åħīæºIJ
    0.11
    夺
    0.10
    èĢĢ
    0.10
    çŀª
    0.10
    太éĺ³
    0.10
    çĴ¨
    0.10
    çħ§
    0.10
    åĪĽæĸ°èĥ½åĬĽ
    0.10
    Activations Density 0.070%

    No Known Activations