© 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. 47603
    Prev
    Next
    INDEX
    Explanations

    immune, exemption, protection

    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
    å°±è¿ij
    -0.11
    _presence
    -0.10
    èĮĦ
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.09
    讲究
    -0.09
    imax
    -0.09
    åIJįçīĩ
    -0.09
    _LCD
    -0.09
    ettle
    -0.08
    éģĩè§ģ
    -0.08
    POSITIVE LOGITS
    åħį
    0.16
    ä¸įåıĹ
    0.15
     khá»ıi
    0.13
     exempt
    0.13
    讵
    0.12
     immune
    0.12
    åħįéĻ¤
    0.11
    åħįçĸ«
    0.11
     exemption
    0.10
     immunity
    0.10
    Activations Density 0.095%

    No Known Activations