© 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. 24149
    Prev
    Next
    INDEX
    Explanations

    catheter implant malfunction

    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
    éĢļè¡Į
    -0.10
    _agents
    -0.09
    uchar
    -0.08
    çľĭäºĨä¸Ģ
    -0.08
    inos
    -0.08
    æĭ¼
    -0.08
    éĢļçĶ¨
    -0.08
     Charg
    -0.08
    gap
    -0.08
    apos
    -0.08
    POSITIVE LOGITS
    æ¤įåħ¥
    0.12
     Trev
    0.09
    æł¸åĩĨ
    0.09
     меÑģÑĤа
    0.09
    èķ¤
    0.09
    åIJįæł¡
    0.08
    奥æŀĹåĮ¹
    0.08
    iances
    0.08
    æİ·
    0.08
    åĭĥ
    0.08
    Activations Density 0.334%

    No Known Activations