© 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. 37240
    Prev
    Next
    INDEX
    Explanations

    feelings and states

    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
    sheets
    -0.09
    æĺ¾å¾Ĺ
    -0.09
    æŀ¢
    -0.09
     fug
    -0.08
    jer
    -0.08
    æľĪä¸ĭ
    -0.08
    çļĦæĹ¥åŃIJ
    -0.08
    ä½Ĩä¸įéĻIJ
    -0.08
    .bytes
    -0.08
    æºĸ
    -0.08
    POSITIVE LOGITS
     rằng
    0.11
    认为
    0.10
    å®ĥæĺ¯
    0.09
    æģ»
    0.09
    èªįçĤº
    0.09
    è¿Ļåıªæĺ¯
    0.09
    社ä¼ļ责任
    0.09
    ock
    0.09
    幸è¿IJ
    0.08
    æĥĭ
    0.08
    Activations Density 0.016%

    No Known Activations