© 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. 29535
    Prev
    Next
    INDEX
    Explanations

    distance measurements

    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
    è¿Ļæł·çļĦè¯Ŀ
    -0.10
    ç¾Ĭæ¯Ľ
    -0.10
    çĶ¨èĩªå·±çļĦ
    -0.09
    åĨĮ
    -0.09
    ä¼´éļıçĿĢ
    -0.09
     fours
    -0.09
    èµ·æŃ¥
    -0.09
    ãĤ·ãĤ¢
    -0.09
    ATUS
    -0.08
    åīĭ
    -0.08
    POSITIVE LOGITS
    æīįç®Ĺ
    0.09
     reactive
    0.09
     ká»ĥ
    0.09
    æľĢéķ¿
    0.09
     fier
    0.08
    æĵį纵
    0.08
    Manip
    0.08
    æľīå¤ļå°ij
    0.08
    åıĶ
    0.08
    ÑĥÑħ
    0.08
    Activations Density 0.081%

    No Known Activations