© 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. 29590
    Prev
    Next
    INDEX
    Explanations

    questions asking for information

    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
    æľīæĦıæĢĿ
    -0.10
    ä¸ĢåľĪ
    -0.09
    åł
    -0.09
    御
    -0.09
     crossword
    -0.08
    rab
    -0.08
    ä»ħæľī
    -0.08
    ANC
    -0.08
    å¤Ķ
    -0.08
    maids
    -0.08
    POSITIVE LOGITS
    éŃĦ
    0.12
    éļ¾éģĵ
    0.10
    olated
    0.10
    ä¼łçľŁ
    0.10
    ekt
    0.09
    anders
    0.09
    è°ģçŁ¥éģĵ
    0.09
    клÑİÑĩа
    0.09
    æĿ²
    0.09
    ä½ķå¿ħ
    0.09
    Activations Density 0.232%

    No Known Activations