© 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. 51689
    Prev
    Next
    INDEX
    Explanations

    prices and quantities

    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
    é«ĺé¢Ŀ
    -0.10
     hôn
    -0.09
    ublic
    -0.09
     обÑıзаÑĤелÑĮно
    -0.09
    AMIL
    -0.09
    è¯ģåĪ¸äº¤æĺĵ
    -0.09
    (iOS
    -0.09
    GRES
    -0.09
    å®ı大
    -0.09
    æ·¡æ·¡
    -0.09
    POSITIVE LOGITS
    ä¹°äºĨ
    0.09
    åı¨
    0.09
    æĪijæĬĬ
    0.09
     Wal
    0.08
     impulse
    0.08
    æīĢ以æĪij
    0.08
    2
    0.08
    åĿıäºĨ
    0.08
    æĺ¯æĪij
    0.08
    è¶ĬæĿ¥
    0.08
    Activations Density 0.043%

    No Known Activations