© 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. 20774
    Prev
    Next
    INDEX
    Explanations

    message saying or asking

    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
    èĩªåľ¨
    -0.10
    ä»»ä½ķæŶåĢĻ
    -0.09
    çľĭä¸Ģçľĭ
    -0.09
    线索
    -0.09
    äºĮ线
    -0.09
    æ¯Ķåĸ»
    -0.09
    äº²çľ¼
    -0.09
    èįª
    -0.09
    èģĮèĥ½éĥ¨éŨ
    -0.09
    èģĮèĥ½
    -0.08
    POSITIVE LOGITS
    ç«ĸ
    0.10
    好åĥıæĺ¯
    0.09
    èѦåijĬ
    0.09
    æİ¥çĿĢ
    0.09
    å¾ĢåIJİ
    0.09
    éļıåį³
    0.09
    æ¡Ĩ
    0.08
    å¾Ģä¸Ĭ
    0.08
    .Designer
    0.08
    pad
    0.08
    Activations Density 0.232%

    No Known Activations