© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9909
    Prev
    Next
    INDEX
    Explanations

    deaths and mortality

    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
    å±ŀ
    -0.08
     оÑĢигинал
    -0.08
    hiba
    -0.08
    èĦı
    -0.08
    è²Į
    -0.08
     gravel
    -0.08
    æŧ
    -0.08
    åIJ¹
    -0.08
    ë³µ
    -0.08
    èĢ½è¯¯
    -0.08
    POSITIVE LOGITS
    ä¸įæŃ»
    0.12
    æľīéĴĪ对æĢ§
    0.12
    æŃ»äº¡
    0.11
    æŃ»åİ»
    0.11
    æŃ»äºĨ
    0.11
    çijļ
    0.10
    ä¸Ģ头
    0.10
    æŃ»èĢħ
    0.10
    çĦ¦
    0.10
    à¸ĩ
    0.10
    Activations Density 0.124%

    No Known Activations