© 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. 16796
    Prev
    Next
    INDEX
    Explanations

    giving or gave

    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
    å®ŀä½ĵ
    -0.10
    è¤Ĵ
    -0.09
    éªIJ
    -0.09
     thÆ°á»Łng
    -0.09
    ä»ij
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    æ·ĸ
    -0.09
    ç»®
    -0.09
    åģļå¾Ĺ
    -0.08
    åĴ»
    -0.08
    POSITIVE LOGITS
    èį«
    0.10
    OI
    0.08
     lectures
    0.08
    forge
    0.08
    éģIJ
    0.08
    åł
    0.08
    ä½İè°ĥ
    0.08
    âĺİ
    0.08
    PRI
    0.08
     himself
    0.08
    Activations Density 0.034%

    No Known Activations