© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2755
    Prev
    Next
    INDEX
    Explanations

    highest grades or ranks

    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
    æī¬
    -0.09
    iswa
    -0.09
    主æĦı
    -0.09
    æīĺ管
    -0.08
    OrNil
    -0.08
    è´ŁåĢº
    -0.08
    åIJĪ
    -0.08
    åıĹçĽĬ
    -0.08
    离å¼ĢäºĨ
    -0.08
    çī¹éķ¿
    -0.08
    POSITIVE LOGITS
    级åĪ«çļĦ
    0.13
    级åĪ«
    0.13
    æľĢé«ĺçļĦ
    0.13
    ç»Īæŀģ
    0.11
    å±Ĥ级
    0.10
    è´µ
    0.10
    顶
    0.10
    ä¸ĸçķĮä¸ĬæľĢ
    0.09
    éĢļè¡Įè¯ģ
    0.09
    å±Ĥ次
    0.09
    Activations Density 0.087%

    No Known Activations