© 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. 52966
    Prev
    Next
    INDEX
    Explanations

    ending or stopping action

    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
    åīĶ
    -0.10
    åĪĨæĺİ
    -0.09
    æĢİä¹Īçľĭ
    -0.09
    ä¸ĢçĤ¹éĥ½ä¸į
    -0.09
    éĢ¼
    -0.09
    æİĴ污
    -0.09
    绣çŃ¹æİ¨è¿Ľ
    -0.09
    鹿
    -0.09
    污
    -0.08
    ưỡng
    -0.08
    POSITIVE LOGITS
    ç®ĹäºĨ
    0.14
    ç½¢äºĨ
    0.10
     дело
    0.10
    оÑģÑĤи
    0.10
    KIT
    0.10
    å°±ç®Ĺ
    0.10
    ç½¢
    0.10
    andas
    0.09
    wat
    0.09
    责任
    0.09
    Activations Density 0.017%

    No Known Activations