© 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. 40339
    Prev
    Next
    INDEX
    Explanations

    avant garde, experimental, artists

    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
    åIJĪãĤıãģĽ
    -0.10
    精彩
    -0.09
     Imam
    -0.09
    -hole
    -0.08
    ยว
    -0.08
    åıijåħī
    -0.08
    oning
    -0.08
    phant
    -0.08
    æľ¬é¢Ĩ
    -0.08
    ä¿Ŀ温
    -0.08
    POSITIVE LOGITS
    人士
    0.11
    çķĮçļĦ
    0.10
    meld
    0.10
    ernal
    0.09
    ä¹ĭä½ľ
    0.09
    icky
    0.09
    æĮĪ
    0.09
    SetActive
    0.09
    è¾Ĥ
    0.09
    迳
    0.09
    Activations Density 0.006%

    No Known Activations