© 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. 59185
    Prev
    Next
    INDEX
    Explanations

    pear plants/cortex/Pearce

    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
    ergy
    -0.09
    holm
    -0.08
    æľ¬çĿĢ
    -0.08
    å¾Ģå¤ĸ
    -0.08
    ÑĢаÑģ
    -0.08
     Ñģка
    -0.08
    æīİ
    -0.08
     Lesser
    -0.08
    åĽ´
    -0.08
    âķ
    -0.08
    POSITIVE LOGITS
    teenth
    0.11
    ffer
    0.10
    entially
    0.10
    prints
    0.10
    çĦ¶æĺ¯
    0.09
    venir
    0.09
    æł·çļĦ
    0.09
    lington
    0.09
    hack
    0.08
    wares
    0.08
    Activations Density 0.004%

    No Known Activations