© 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. 37519
    Prev
    Next
    INDEX
    Explanations

    married, mature, politics, seeking men

    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
    éĩİ
    -0.08
    ctal
    -0.08
    å¸ĪèµĦ
    -0.08
    kest
    -0.08
    ÙĤا
    -0.08
    åĩ¿
    -0.08
    cia
    -0.08
    ÑħваÑĤ
    -0.08
    aken
    -0.08
    æĻ®åıĬ
    -0.08
    POSITIVE LOGITS
    è·Łä»ĸ
    0.10
    åIJĮçŃī
    0.09
    å°ı康
    0.09
    女æĸ¹
    0.09
     Mutual
    0.09
    约ä¼ļ
    0.09
     vá»ĩ
    0.09
    纲
    0.09
    çģ¯çģ«
    0.09
     veto
    0.09
    Activations Density 0.047%

    No Known Activations