© 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. 8552
    Prev
    Next
    INDEX
    Explanations

    e-commerce

    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
    æīĶ
    -0.08
    lest
    -0.08
    stell
    -0.08
    å°¤åħ¶æĺ¯åľ¨
    -0.08
    erne
    -0.08
    鹧
    -0.08
    ä¸ŃåĽ½çī¹èī²
    -0.08
    jerne
    -0.07
    finder
    -0.07
    izations
    -0.07
    POSITIVE LOGITS
    ÙħاÙĦ
    0.10
    bers
    0.10
    presso
    0.09
    è°¯
    0.09
    /jav
    0.09
    çĭIJ
    0.09
    éĽĨåĽ¢èĤ¡ä»½
    0.09
    è°ļ
    0.09
    æĹ¶ä»£ä¸ŃåĽ½
    0.09
    ickle
    0.09
    Activations Density 0.012%

    No Known Activations