© 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. 21253
    Prev
    Next
    INDEX
    Explanations

    younger people, loyal people, dreamers

    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
    å§Ĭ
    -0.09
    è¿Ļ两天
    -0.08
     Urs
    -0.08
    èĩ³ä»Ĭ
    -0.08
    inks
    -0.08
    éķ¿æľŁä»¥æĿ¥
    -0.08
    è¹Ħ
    -0.08
    å§Ĭ妹
    -0.08
    ç¾ģ
    -0.08
    èĤĩ
    -0.08
    POSITIVE LOGITS
    éģĵåħ·
    0.11
    主人åħ¬
    0.11
    çĶ·ä¸»è§Ĵ
    0.11
    åŀ¦
    0.10
    çĶ·ä¸»
    0.10
    ç¯ĩ
    0.10
    åĮ»
    0.10
    æĸĩä¸Ń
    0.10
    伤亡
    0.09
    贯穿
    0.09
    Activations Density 0.245%

    No Known Activations