© 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. 37301
    Prev
    Next
    INDEX
    Explanations

    whole wheat, cells, virus, body, embryo, blood

    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
    å¾Ģäºĭ
    -0.10
    æļ®
    -0.10
    桦
    -0.09
    èĻIJå¾ħ
    -0.09
    é«ĺ楼
    -0.09
     Witt
    -0.08
    è¦ģæĬĬ
    -0.08
     ÑĤож
    -0.08
    nü
    -0.08
    æĿ²
    -0.08
    POSITIVE LOGITS
    /full
    0.09
    å±ij
    0.09
    anced
    0.09
    åŃļ
    0.09
     intact
    0.09
    ä¸Ńåħ³
    0.08
    è¯Ŀ说
    0.08
    对æİ¥
    0.08
    ç½ijç«Ļåľ°åĽ¾
    0.08
     lear
    0.08
    Activations Density 0.011%

    No Known Activations