© 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. 1269
    Prev
    Next
    INDEX
    Explanations

    Ericsson

    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
    IRS
    -0.10
    建档
    -0.10
    æĪIJé¾Ļ
    -0.09
    ASTE
    -0.09
    檩
    -0.09
    æģĿ
    -0.09
    æ¤ĭ
    -0.09
    è¿ŀ线
    -0.09
    æīĵåĩ»
    -0.09
    家ä¼Ļ
    -0.08
    POSITIVE LOGITS
    妾
    0.10
    lish
    0.09
     Airways
    0.09
     Cups
    0.09
    èĩªæĦ¿
    0.09
    ween
    0.09
     Meer
    0.08
    è¿Ļä¸Ģ次
    0.08
    微信
    0.08
    éĺ³æĢ§
    0.08
    Activations Density 0.001%

    No Known Activations