© 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. 6124
    Prev
    Next
    INDEX
    Explanations

    accurate diagnosis

    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
    otron
    -0.09
    è¯
    -0.09
    éĶ°
    -0.09
    é¢Ħå¤ĩ
    -0.09
    stub
    -0.08
    çĸ®
    -0.08
    é²ģ
    -0.08
    éĽĨ
    -0.08
    tim
    -0.08
    stay
    -0.08
    POSITIVE LOGITS
    YLE
    0.10
    åĸĦèī¯
    0.09
    éĿŀçī©è´¨
    0.09
    å®ĮæĪIJåIJİ
    0.09
    æĭĶ
    0.09
    reator
    0.09
    oup
    0.09
    绣
    0.09
    å¿ĥè¡Ģ
    0.08
     laure
    0.08
    Activations Density 0.179%

    No Known Activations