© 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. 36793
    Prev
    Next
    INDEX
    Explanations

    a lot

    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
    ichi
    -0.10
    æľīåºı
    -0.09
    tributes
    -0.08
    ย
    -0.08
    åİ®
    -0.08
    解åĨ³äºĨ
    -0.08
    ä»Ģä¹Īåľ°æĸ¹
    -0.08
     à¹Ĩ
    -0.08
    èĥ¥
    -0.08
    et
    -0.08
    POSITIVE LOGITS
    å¾Ī强
    0.15
    åīįéĢĶ
    0.13
    å¾Īé«ĺçļĦ
    0.13
    å¾Ī好çļĦ
    0.12
    å¾Īæ·±
    0.11
    éĿŀ常好çļĦ
    0.11
    éĿŀ常好
    0.10
    /use
    0.09
    æĮĪ
    0.09
    éĤ£ä¹Īå¤ļ
    0.09
    Activations Density 0.090%

    No Known Activations