© 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. 37234
    Prev
    Next
    INDEX
    Explanations

    Nile Parker

    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
    ëĿ¼ëıĦ
    -0.09
    ä»ģ
    -0.09
    APA
    -0.08
    åģļåĪ°äºĨ
    -0.08
    åĬłä»¥
    -0.08
    æĸ©
    -0.08
    ä¸ĢåĪ»
    -0.08
    åī²
    -0.08
    ç³»åĪĹ产åĵģ
    -0.08
    Greg
    -0.08
    POSITIVE LOGITS
    ÄĻd
    0.10
    æľįåĬ¡è´¨éĩı
    0.09
    æĦŁåºĶ
    0.09
    èĮĮ
    0.08
     gou
    0.08
    ends
    0.08
    ogg
    0.08
     Horton
    0.08
    éĤ¯
    0.08
    妲
    0.08
    Activations Density 0.013%

    No Known Activations