© 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. 16874
    Prev
    Next
    INDEX
    Explanations

    media and press companies

    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
    Not in Any Lists

    No Comments

    Negative Logits
    osite
    -0.10
    bare
    -0.10
    deposit
    -0.09
    PathParam
    -0.09
    æī§ä¸ļ
    -0.08
     bare
    -0.08
    assist
    -0.08
    _locator
    -0.08
    åIJĦ家
    -0.08
     FIT
    -0.08
    POSITIVE LOGITS
    æĹĹä¸ĭ
    0.11
    éĽĨåĽ¢
    0.11
    éĽªèĬ±
    0.09
    anel
    0.09
    äºĶåĽĽ
    0.09
    é¾Į
    0.09
    éĽĨåĽ¢æĹĹä¸ĭ
    0.09
    æľīéĻIJ
    0.09
    æݧèĤ¡éĽĨåĽ¢
    0.09
    å¼Ĭ
    0.08
    Activations Density 0.068%

    No Known Activations