© 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. 61017
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by prepositions or adverbs

    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
    æѤ类
    -0.10
    è¿Ļéĥ¨åĪĨ
    -0.10
    端åįĪ
    -0.10
    åħĥæŦ
    -0.09
    è¿Ļç±»
    -0.09
    кам
    -0.09
     Bath
    -0.09
    atern
    -0.09
    鸾
    -0.09
    æĸ°å¹´
    -0.08
    POSITIVE LOGITS
    ︵
    0.08
    带åĪ°
    0.08
     cou
    0.08
    ä½¼
    0.08
    ذر
    0.08
     chap
    0.08
     Rooney
    0.08
    çļĦæĹ¥åŃIJéĩĮ
    0.08
    票
    0.08
    åıĤä¸İåĪ°
    0.08
    Activations Density 0.394%

    No Known Activations