© 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. 21667
    Prev
    Next
    INDEX
    Explanations

    of the United 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
    åĢį
    -0.11
    åIJİçļĦ
    -0.09
     fooled
    -0.09
    äºīåIJµ
    -0.08
    å®Ĺ
    -0.08
    ERIC
    -0.08
    sville
    -0.08
    ÑĭÑĪ
    -0.08
    åĬŀ好
    -0.08
    ifax
    -0.08
    POSITIVE LOGITS
    ä¸Ńåįİ人æ°ij
    0.13
    åħ±åĴĮåĽ½
    0.10
    åħ±äº§åħļ
    0.10
     ÐłÐ¾ÑģÑģийÑģкой
    0.10
    大ä¼Ĺ
    0.10
    èµĦ
    0.10
    è¡·å¿ĥ
    0.09
    èĨĤ
    0.09
    bai
    0.09
    ä¸Ģæĸ¹
    0.09
    Activations Density 0.226%

    No Known Activations