© 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. 52051
    Prev
    Next
    INDEX
    Explanations

    second cause of death

    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
    ç§ĺ
    -0.10
    é«ĺ端
    -0.09
    åį±
    -0.09
    çĩĥ
    -0.08
    ç®ķ
    -0.08
    åĨľå®¶
    -0.08
    çļĦæĸ¹å¼ıæĿ¥
    -0.08
    裸
    -0.08
    对èĩªå·±çļĦ
    -0.08
    зал
    -0.08
    POSITIVE LOGITS
    ä»ħ次äºİ
    0.15
    第äºĮ大
    0.15
    åħ¨çIJĥæľĢ大
    0.13
    ä¸ĸçķĮä¸Ĭ
    0.12
     Largest
    0.11
     CONTRIBUTORS
    0.11
    æİĴåIJį
    0.11
    ä»ħ次
    0.10
    -volume
    0.10
    ä¸ĸçķĮä¸ĬæľĢ
    0.10
    Activations Density 0.270%

    No Known Activations