© 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. 20724
    Prev
    Next
    INDEX
    Explanations

    I've been

    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
    ç¾İ好çļĦ
    -0.10
    æłĵ
    -0.10
    ä¸ĢåĪĨéĴ±
    -0.09
    uru
    -0.09
    ãģĵãģĵãģ¾ãģ§
    -0.09
    åĽĽå¤§
    -0.08
    对å¾ħ
    -0.08
    æľī人
    -0.08
    .enumer
    -0.08
    ãģłãģ£ãģ¦
    -0.08
    POSITIVE LOGITS
    æĦŁåħ´è¶£çļĦ
    0.11
    è¾ĥå¤ļ
    0.11
    çłĶ究
    0.11
    åħ´è¶£
    0.11
    è¿ĻäºĽå¹´
    0.10
    éŀį
    0.10
    çļĦåħ´è¶£
    0.10
    æݢ索
    0.10
    ä¸ĢçĽ´åľ¨
    0.10
    æ¯Ķè¾ĥå¤ļ
    0.10
    Activations Density 0.202%

    No Known Activations