© 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. 60748
    Prev
    Next
    INDEX
    Explanations

    comparison words

    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
    æĽ´å¥½
    -0.11
    æĺ¯æľĢ好çļĦ
    -0.10
    空åīį
    -0.10
    çĿ£åĬŀ
    -0.10
    寻常
    -0.10
    åĽ½æľī
    -0.09
    åĽ¿
    -0.09
    ترا
    -0.09
    омн
    -0.09
    WithURL
    -0.09
    POSITIVE LOGITS
    TYPO
    0.09
     Jew
    0.09
    ALSE
    0.09
    æĭĴä¸į
    0.08
    ogy
    0.08
    çıł
    0.08
    èĭĶ
    0.08
    ally
    0.08
    人们
    0.08
     PACK
    0.08
    Activations Density 0.042%

    No Known Activations