© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34173
    Prev
    Next
    INDEX
    Explanations

    people or 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
    丢äºĨ
    -0.09
    ä¸Ĭæ¼Ķ
    -0.09
    éĢļ常æĺ¯
    -0.09
    温åĴĮ
    -0.09
    åŁºéĩij管çIJĨ
    -0.09
    解读
    -0.09
    åĺĽ
    -0.08
    .li
    -0.08
    ç¿Ĭ
    -0.08
    angi
    -0.08
    POSITIVE LOGITS
    æīĭä¸ŃçļĦ
    0.10
    ìĹIJê²Į
    0.10
    çļĦ产åĵģ
    0.10
    ãģķãĤĵãģ®
    0.09
    家ãģ®
    0.09
    çļĦäºĭæĥħ
    0.09
    .Enum
    0.09
    æij
    0.09
    æ¯ı个人çļĦ
    0.09
    ä¹ĭä½ľ
    0.09
    Activations Density 0.754%

    No Known Activations