© 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. 24065
    Prev
    Next
    INDEX
    Explanations

    showing results, display, viewing

    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
    REA
    -0.10
    æĿ¥äºĨ
    -0.10
    .ov
    -0.09
    表çĻ½
    -0.09
    CodeGen
    -0.09
    -heart
    -0.09
    沸
    -0.09
    æıŃå¼Ģ
    -0.09
    迨
    -0.09
    pine
    -0.08
    POSITIVE LOGITS
    æģ¨
    0.09
    å°¾
    0.09
    orra
    0.09
    æĤį
    0.08
    åijĪçİ°
    0.08
     sorted
    0.08
    èĩªåįij
    0.08
    ãģ»ãģ©
    0.08
    é¹Ī
    0.08
    éĢIJ
    0.08
    Activations Density 0.006%

    No Known Activations