© 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. 35546
    Prev
    Next
    INDEX
    Explanations

    when followed by pronoun/noun

    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
    æŃ£åľ¨
    -0.10
    ä½ı
    -0.09
    .hh
    -0.08
    _upd
    -0.08
     understandably
    -0.08
    gest
    -0.08
    é»ijé¾Ļ
    -0.08
    å¹»
    -0.08
    .getIn
    -0.08
    idency
    -0.08
    POSITIVE LOGITS
    人们对
    0.11
    ä½łä¸į
    0.10
    çĥŃå¿ĥ
    0.09
    书éĿ¢
    0.09
    ä¸Ģ对
    0.09
    人å¿ĥ
    0.09
    ç¿»å¼Ģ
    0.09
    人æ°Ķ
    0.09
    ä»·æł¼ä¸Ĭ涨
    0.09
    ãĥijãĤ¿
    0.09
    Activations Density 0.179%

    No Known Activations