© 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. 20940
    Prev
    Next
    INDEX
    Explanations

    professionals and their roles

    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
    agner
    -0.10
    åı²ä¸Ĭ
    -0.09
    ä¸īåĨľ
    -0.09
    æĹłæĥħ
    -0.09
    åľºéĿ¢
    -0.09
    å¼¢
    -0.09
    鸽
    -0.09
    Svc
    -0.09
    erson
    -0.09
    ç§ijæĬĢèĤ¡ä»½
    -0.09
    POSITIVE LOGITS
    INGS
    0.10
    ëĬIJ
    0.09
    ings
    0.08
    ests
    0.08
    ä¾Ľå¤§å®¶
    0.08
    éķ±
    0.08
    utions
    0.08
    ÑİÑī
    0.08
    ICAL
    0.08
    ÇĴ
    0.08
    Activations Density 0.185%

    No Known Activations