© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48448
    Prev
    Next
    INDEX
    Explanations

    famous individuals

    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
    ä¸Ģä½į
    -0.10
    åĵ¥åĵ¥
    -0.09
    ä¸¤åľ°
    -0.09
    onen
    -0.09
    快讯
    -0.09
    itre
    -0.09
    å¤ļä½į
    -0.09
    主ä¹īæĢĿæĥ³
    -0.09
    onna
    -0.09
    们éĥ½
    -0.09
    POSITIVE LOGITS
     inev
    0.09
    ickle
    0.08
    äºĨäºĽ
    0.08
    æĢ§æł¼
    0.08
     THR
    0.08
    ä¸įæŃ¢
    0.08
    çļĦçĶŁæ´»
    0.08
    éĹ´æİ¥
    0.08
    dem
    0.07
     Sundays
    0.07
    Activations Density 0.048%

    No Known Activations