© 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. 38428
    Prev
    Next
    INDEX
    Explanations

    studied at university

    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
    æķŀ
    -0.10
    æłª
    -0.10
    æĹłåģ¿
    -0.09
    鸡汤
    -0.09
    åIJĮç±»
    -0.09
    çݯèĬĤ
    -0.09
    ä¸ĢæĬĬ
    -0.09
    ÅĤow
    -0.09
    ä¸Ģåı¥è¯Ŀ
    -0.09
    ÃľN
    -0.09
    POSITIVE LOGITS
    åĩºèº«
    0.10
    带头人
    0.08
    alon
    0.08
    ä¸ĵä¸ļçļĦ
    0.08
    éĥ¨
    0.08
    alic
    0.08
    æĤłä¹ħ
    0.08
    ặc
    0.07
    sky
    0.07
    _py
    0.07
    Activations Density 0.099%

    No Known Activations