© 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. 7806
    Prev
    Next
    INDEX
    Explanations

    information processing

    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
    åħ»èĢģéĩij
    -0.10
    æĬ¼
    -0.10
    漫
    -0.10
    PropertyDescriptor
    -0.09
    æ·¤
    -0.09
    çĦ°
    -0.09
    大象
    -0.08
    ç£ĭ
    -0.08
     Ñĩа
    -0.08
     skÅĤ
    -0.08
    POSITIVE LOGITS
    è¾£
    0.10
    igma
    0.10
    鼳
    0.09
    æķĪçĽĬ
    0.09
    æĿIJ
    0.08
     Huffman
    0.08
    åĤ¨åŃĺ
    0.08
     probe
    0.08
    è®°å½ķ
    0.08
    ç¼ĸçłģ
    0.08
    Activations Density 0.311%

    No Known Activations