© 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. 36589
    Prev
    Next
    INDEX
    Explanations

    mounting evidence

    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
    è´¢åĬ¡ç®¡çIJĨ
    -0.09
    贪婪
    -0.09
    ä¼ĺåħĪ
    -0.09
    icions
    -0.09
    IGIN
    -0.08
    路桥
    -0.08
    åIJijåīį
    -0.08
    åĪĨå·¥
    -0.08
    inic
    -0.08
    ienes
    -0.08
    POSITIVE LOGITS
    人们对
    0.10
    æķ²
    0.10
    èµ·æĿ¥
    0.10
    åįĩ温
    0.09
    æ°ĶåĬ¿
    0.09
     dần
    0.09
    缴èĩ³
    0.09
    éĺ¶
    0.08
    udo
    0.08
    frag
    0.08
    Activations Density 0.083%

    No Known Activations