© 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. 10374
    Prev
    Next
    INDEX
    Explanations

    genetic and medical consent

    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
    ych
    -0.10
    æī¬å°ĺ
    -0.09
    ä½ľé£İ
    -0.09
    æ·¹
    -0.09
    é©»æĿij
    -0.09
    å®īåħ¨çĶŁäº§
    -0.09
    派驻
    -0.09
    çĸ«æĥħæľŁéĹ´
    -0.08
    å¿ĥçIJĨåѦ
    -0.08
    çļĦèĥ½éĩı
    -0.08
    POSITIVE LOGITS
    ç§ijåŃ¦å®¶
    0.12
    è¯ķ管
    0.11
    æįIJçĮ®
    0.11
    ç§ijçłĶ
    0.11
     scientists
    0.10
    ç§ijåѦ
    0.10
    ç§ijæĬĢ
    0.10
     sci
    0.09
     consent
    0.09
    åķĨä¸ļåĮĸ
    0.09
    Activations Density 0.115%

    No Known Activations