© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16679
    Prev
    Next
    INDEX
    Explanations

    ducking, kneeling, low position

    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
    Negative Logits
     upt
    -0.10
    è¿Ń
    -0.09
    idor
    -0.09
    dead
    -0.09
    è§Ħæł¼
    -0.09
    åįķåĵģ
    -0.09
    ä»·æł¼ä¸Ĭ涨
    -0.08
    ãĥĻãĥ³
    -0.08
    izo
    -0.08
    è§ĦèĮĥåĮĸ
    -0.08
    POSITIVE LOGITS
    çĶŁæĢģä¿ĿæĬ¤
    0.09
    ä¸ĭæĿ¥
    0.09
    nement
    0.09
    acks
    0.09
    乩
    0.09
    è¸ŀ
    0.09
     Medi
    0.09
    erd
    0.09
     Shotgun
    0.09
    ISTR
    0.09
    Activations Density 0.010%

    No Known Activations