© 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. 12282
    Prev
    Next
    INDEX
    Explanations

    favorable or unfavorable outcomes and prognosis

    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
    æĪIJåĬŁä¸¾åĬŀ
    -0.09
    ãĥĥãĤ°
    -0.09
    é²ľèĬ±
    -0.09
    çĭĤ欢
    -0.09
    ä¸ĭæ²ī
    -0.09
    åIJįçīĮ
    -0.09
    akra
    -0.09
    两åı¥
    -0.09
     اÙĦعاصÙħØ©
    -0.08
     bada
    -0.08
    POSITIVE LOGITS
    å¼Ģ端
    0.10
    èIJ¥åķĨ
    0.09
    ä¸įèĥ½åĨį
    0.09
    éĢŁ
    0.09
    èĢķ
    0.09
    etus
    0.08
     enough
    0.08
     tide
    0.08
    ä¸īæĸ¹
    0.08
    emm
    0.08
    Activations Density 0.041%

    No Known Activations