© 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. 12387
    Prev
    Next
    INDEX
    Explanations

    resection surgery

    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
    åij¨è½¬
    -0.10
    è¯Ń
    -0.09
    è¿ĩå¾Ģ
    -0.09
    æ»´
    -0.09
     Nail
    -0.09
    ilon
    -0.09
    é©°
    -0.09
    /grid
    -0.09
    itious
    -0.09
    -guide
    -0.08
    POSITIVE LOGITS
    åī²
    0.12
    离å¼ĢäºĨ
    0.10
     единÑģÑĤв
    0.10
    åīľ
    0.10
    èĥ½æī¾åĪ°
    0.09
    æijĺ
    0.09
    åĪĩéĻ¤
    0.09
    åѤç«ĭ
    0.09
    è¢į
    0.09
    im
    0.09
    Activations Density 0.215%

    No Known Activations