© 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. 37759
    Prev
    Next
    INDEX
    Explanations

    look at

    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
    å·¥ä½ľçļĦ
    -0.09
    æİĮæı¡äºĨ
    -0.08
    åIJ¸åħ¥
    -0.08
    å¿Ĺ强
    -0.08
    妥
    -0.08
    ä¼¼ä¹İæĺ¯
    -0.08
     Schmidt
    -0.08
    å¾ĹäºĨ
    -0.08
    为äºĨæĽ´å¥½
    -0.07
    æĬµæĬĹåĬĽ
    -0.07
    POSITIVE LOGITS
    审è§Ĩ
    0.11
    çľĭå¾ħ
    0.10
    éĢĥçĶŁ
    0.10
    éŀł
    0.10
    æĴĴ
    0.10
    æīª
    0.10
    æľĽåİ»
    0.09
    ä¸Ĭçľĭ
    0.09
    OMET
    0.09
    ç²²
    0.09
    Activations Density 0.022%

    No Known Activations