© 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. 16558
    Prev
    Next
    INDEX
    Explanations

    wearable tech and hardware

    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
    许
    -0.10
    ãĥĮ
    -0.09
    æ°´æµģ
    -0.09
    çĨĶ
    -0.09
    åIJĽ
    -0.09
    æIJĸ
    -0.08
    æľīåĬĽ
    -0.08
    éĨ¬
    -0.08
    anium
    -0.08
    prs
    -0.08
    POSITIVE LOGITS
    家åĬ¡
    0.11
    åĻ¨åħ·
    0.11
    åĪ¶åĵģ
    0.11
     items
    0.11
    çĶ¨åĵģ
    0.10
    é½IJåħ¨
    0.10
    件
    0.10
     accessories
    0.10
    éħį件
    0.10
     Gad
    0.09
    Activations Density 0.091%

    No Known Activations