© 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. 17699
    Prev
    Next
    INDEX
    Explanations

    the relative clause connector

    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
    çľ¼éĩĮ
    -0.11
    æľī许å¤ļ
    -0.10
    .lv
    -0.10
    EEP
    -0.10
    æľīå¾Ī大
    -0.09
    çľ¼ä¸Ń
    -0.09
    coin
    -0.09
    ä¸Ńæľī
    -0.09
    æľīè¶³å¤ŁçļĦ
    -0.09
    aised
    -0.09
    POSITIVE LOGITS
    soever
    0.12
    å®ĥ们
    0.10
    'er
    0.09
    s
    0.08
    rames
    0.08
    æĽ´éĩįè¦ģçļĦ
    0.08
    ä¾
    0.08
    æįŁ
    0.08
    eve
    0.08
     oneself
    0.08
    Activations Density 0.033%

    No Known Activations