© 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. 36040
    Prev
    Next
    INDEX
    Explanations

    toilet facilities

    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
    æĩĭ
    -0.10
    é¢ĺ主
    -0.10
    skin
    -0.09
    ollo
    -0.09
    æ¥Ķ
    -0.09
    çļĦçĪ±æĥħ
    -0.09
    æĢĢæĬ±
    -0.09
    æ·±æĥħ
    -0.09
    è§ĨåĬĽ
    -0.09
    ɣ
    -0.09
    POSITIVE LOGITS
    裤åŃIJ
    0.11
    æİĴ污
    0.10
    马桶
    0.10
    tee
    0.09
    èĤĽ
    0.09
    3
    0.09
    åį«çĶŁ
    0.09
     sto
    0.09
    裤
    0.09
    5
    0.09
    Activations Density 0.097%

    No Known Activations