© 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. 6254
    Prev
    Next
    INDEX
    Explanations

    you all / you guys

    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
    åĽĬ
    -0.10
    iero
    -0.10
    tem
    -0.09
    lr
    -0.09
     SIG
    -0.08
     pros
    -0.08
    orny
    -0.08
    è¿Ļåıª
    -0.08
    REP
    -0.08
    ORY
    -0.08
    POSITIVE LOGITS
    uded
    0.11
    沫
    0.10
    urple
    0.10
    æĮº
    0.09
    .createElement
    0.09
    aled
    0.09
    ANGER
    0.08
    æĶ¾å¼Ģ
    0.08
    acades
    0.08
    ilder
    0.08
    Activations Density 0.007%

    No Known Activations