© 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. 22215
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs starting questions

    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
    æĹ¢åı¯ä»¥
    -0.12
    acco
    -0.09
    èĩ³äºİ
    -0.09
    ç¿¡
    -0.09
    ä¸įå¤ļ
    -0.08
    æIJª
    -0.08
    åIJ»
    -0.08
    æĹ¢èĥ½
    -0.08
    .paging
    -0.08
    ulp
    -0.08
    POSITIVE LOGITS
    没åħ³ç³»
    0.13
    åħ¶ä»ĸçļĦ
    0.12
    åħ¶ä»ĸ
    0.11
    ä¹Łä¸įèĥ½
    0.11
    ãģĿãĤĮãģ§ãĤĤ
    0.10
    ä¹Łä¸įä¼ļ
    0.10
    ä¹Łä¸į
    0.10
    ä¹Łæ²¡
    0.10
    åĪĻ
    0.10
     nor
    0.10
    Activations Density 0.083%

    No Known Activations