© 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. 38143
    Prev
    Next
    INDEX
    Explanations

    Guatemala, chrome, mercury, Br

    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
    èĥ½åĬĽåĴĮ
    -0.12
    æĢ§åĴĮ
    -0.11
    管çIJĨåĴĮ
    -0.11
    ç»ıéªĮåĴĮ
    -0.10
    ä¹Łæĺ¯ä¸Ģ个
    -0.10
    æĬĢæľ¯åĴĮ
    -0.10
    æĺ¯ä¸Ģ项
    -0.09
    ä»ĸæĺ¯ä¸Ģ个
    -0.09
    çļĦä¸ĢåĪĩ
    -0.09
    æľī两个
    -0.09
    POSITIVE LOGITS
    éĥ½å¾Ī
    0.15
    åIJĦèĩªçļĦ
    0.15
     alike
    0.15
    åIJĦèĩª
    0.15
    åIJĦæľī
    0.13
    çŃī人
    0.13
     respectively
    0.13
    éĥ½éĿŀ常
    0.13
    以åıĬ
    0.13
    éĥ½æĺ¯
    0.13
    Activations Density 0.356%

    No Known Activations