© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 22139
    Prev
    Next
    INDEX
    Explanations

    coach or manager titles

    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
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    åģ¥åº·æĪIJéķ¿
    -0.09
    èĢIJ磨
    -0.09
    .invalidate
    -0.09
     Cly
    -0.08
    ippers
    -0.08
    å°ıä¼Ļ伴们
    -0.08
    å¤Ń
    -0.08
    ç§ijæĬĢèĤ¡ä»½
    -0.08
    inger
    -0.08
    POSITIVE LOGITS
    æī§æķĻ
    0.17
    带é¢Ĩ
    0.16
    ä»»æľŁ
    0.14
    带éĺŁ
    0.12
    çİĩé¢Ĩ
    0.11
    èģĮç§°
    0.11
     teaching
    0.11
    ä»»æķĻ
    0.10
    mgr
    0.10
    æ®ļ
    0.10
    Activations Density 0.227%

    No Known Activations