© 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. 9159
    Prev
    Next
    INDEX
    Explanations

    physical and medical health evaluations

    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
    åĪĩ
    -0.09
    arms
    -0.09
    åĮª
    -0.09
    è½½
    -0.08
    没äºĭ
    -0.08
     ISA
    -0.08
     chalk
    -0.08
    è¼ī
    -0.08
    çļĦ好
    -0.08
    cé
    -0.08
    POSITIVE LOGITS
    èĻ»
    0.10
    躯
    0.10
    æ´µ
    0.09
    æĮĩæĮ¥
    0.09
    ä½
    0.09
    BOR
    0.09
    çݯå¢ĥä¸Ń
    0.09
    stry
    0.09
    Bins
    0.09
    åİ¥
    0.09
    Activations Density 0.480%

    No Known Activations