© 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. 64070
    Prev
    Next
    INDEX
    Explanations

    emerging tools, brands, models, markets, technologies

    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
    çĽĬ
    -0.10
    yt
    -0.09
    èĬĥ
    -0.09
    alty
    -0.08
    maker
    -0.08
    æĤłä¹ħ
    -0.08
    lush
    -0.08
    累累
    -0.08
    ians
    -0.08
    é¾Ľ
    -0.08
    POSITIVE LOGITS
    idget
    0.11
    æĸ°åħ´
    0.10
    æŃ£åĽłä¸º
    0.10
    éĥľ
    0.10
    æĪIJçĨŁ
    0.09
    aticon
    0.09
    ãĥ¬ãĤ¹ãĥĪ
    0.09
    æĽ´éĩįè¦ģçļĦ
    0.09
    .recycle
    0.09
    สาร
    0.09
    Activations Density 0.015%

    No Known Activations