© 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. 10123
    Prev
    Next
    INDEX
    Explanations

    school activities and groups

    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
    ä¾ł
    -0.09
    æĿĥ
    -0.09
     Shoes
    -0.08
     boots
    -0.08
     Ara
    -0.08
    å¥Ķ
    -0.08
    èĩªç§ģ
    -0.08
    åºĵ
    -0.08
     TestCase
    -0.08
    usto
    -0.08
    POSITIVE LOGITS
    çĶ·çĶŁ
    0.10
    éĴī
    0.09
    åŃ¦æł¡çļĦ
    0.08
    éĢļé£İ
    0.08
     Ding
    0.08
    é¢ĵ
    0.08
     ding
    0.08
    èı±
    0.08
    寰
    0.08
    çļĦåŃĺåľ¨
    0.08
    Activations Density 0.123%

    No Known Activations