© 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. 6939
    Prev
    Next
    INDEX
    Explanations

    Auxiliary verbs like 'do' and 'did'

    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
    pch
    -0.12
    AtA
    -0.11
    ORA
    -0.11
    羡
    -0.10
    åµ´
    -0.09
    使çĶ¨çļĦ
    -0.09
     mexico
    -0.09
     HMS
    -0.09
    oran
    -0.09
    è§
    -0.09
    POSITIVE LOGITS
    çļĦéĤ£ç§į
    0.11
    å¾ĪæŃ£å¸¸
    0.10
    åĸĦäºİ
    0.10
    éĤ£ç§į
    0.09
    zoom
    0.09
    岸
    0.08
    kü
    0.08
    宫
    0.08
    hone
    0.08
    转åĮĸ
    0.08
    Activations Density 0.063%

    No Known Activations