© 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. 60611
    Prev
    Next
    INDEX
    Explanations

    you want

    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
     Kinect
    -0.08
    æľīæĽ´å¥½çļĦ
    -0.08
    ables
    -0.08
    kins
    -0.07
     Franken
    -0.07
    åĩºè·¯
    -0.07
    æĪĸåħ¶ä»ĸ
    -0.07
    Kin
    -0.07
     lest
    -0.07
    arie
    -0.07
    POSITIVE LOGITS
    驹
    0.12
    让å®ĥ
    0.11
    æĪijçĽ¸ä¿¡
    0.10
    称ä¹ĭ
    0.10
    é¼
    0.09
    odash
    0.09
    飫
    0.09
    ä¾ij
    0.09
    æĪĺçģ«
    0.09
    æĪij认为
    0.09
    Activations Density 0.028%

    No Known Activations