© 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. 36746
    Prev
    Next
    INDEX
    Explanations

    companies and organizations

    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
    åIJĪçIJĨçļĦ
    -0.10
    çĪ±æĥħ
    -0.09
    æľĢå¿«çļĦ
    -0.09
    笺
    -0.09
    ä¿Ŀåį«
    -0.09
    çij¾
    -0.08
    éĴĹ
    -0.08
    è£Ĥç¼Ŀ
    -0.08
    æįķ
    -0.08
    éĵ¤
    -0.08
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.09
    ÑģилÑĮ
    0.09
    hort
    0.08
    mát
    0.08
    ersed
    0.08
    ContentLoaded
    0.08
    éŃĦ
    0.08
    ActionResult
    0.08
    é¾Ľ
    0.08
    åĸĦæĦı
    0.08
    Activations Density 0.218%

    No Known Activations