© 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. 8426
    Prev
    Next
    INDEX
    Explanations

    twitter handles and blogs

    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
    éĤ£æ¬¡
    -0.09
     founders
    -0.09
     itself
    -0.09
    ÑĪив
    -0.08
    lore
    -0.08
    ä¸Ģ次
    -0.08
    以æĿ¥
    -0.08
     ourselves
    -0.08
     Bott
    -0.08
    ä½į
    -0.08
    POSITIVE LOGITS
    çĮ·
    0.10
    åĽĽä¸ªæĸ¹éĿ¢
    0.10
    è¨Ģè¡Į
    0.10
    ä»ĸ对
    0.10
    ä½ľä¸ºä¸ĢåIJį
    0.10
    ä»ĸæĺ¯
    0.09
    çĺ¦
    0.09
    åı¹
    0.09
    个人è§ĤçĤ¹
    0.09
    åı¤åħ¸
    0.09
    Activations Density 0.033%

    No Known Activations