© 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. 51550
    Prev
    Next
    INDEX
    Explanations

    property and element names

    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
    arda
    -0.09
    æĸ°è¥¿
    -0.08
    快讯
    -0.08
    åįĬ个
    -0.07
    人éĹ´
    -0.07
    å½»
    -0.07
    SEG
    -0.07
    çīĩ段
    -0.07
     Pens
    -0.07
    аÑĢа
    -0.07
    POSITIVE LOGITS
    å±ŀæĢ§
    0.14
    åŃĹ段
    0.11
     property
    0.11
    å±Ļ
    0.11
    è¿Ļ项
    0.10
    æ¬Ħ
    0.10
    ä¸Ģ项
    0.10
    åĢ¼
    0.10
     value
    0.10
     attribute
    0.10
    Activations Density 1.147%

    No Known Activations