© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36452
    Prev
    Next
    INDEX
    Explanations

    serve you

    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
    对å¤ĸ
    -0.09
    çļĦ社ä¼ļ
    -0.09
    人人
    -0.08
    ette
    -0.08
    åİ®
    -0.08
    蹶
    -0.08
    马æĿ¥
    -0.08
    çļĦçĶŁæ´»
    -0.08
    åħijçİ°
    -0.08
    пÑĥÑģÑĤ
    -0.08
    POSITIVE LOGITS
    大å±Ģ
    0.11
    人æ°ijæľįåĬ¡
    0.10
    åĽ½å®¶æĪĺçķ¥
    0.09
    èº²åľ¨
    0.09
    æĢģ度
    0.09
    æģļ
    0.09
    udios
    0.09
     mieux
    0.09
    omez
    0.08
    社群
    0.08
    Activations Density 0.038%

    No Known Activations