© 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. 16678
    Prev
    Next
    INDEX
    Explanations

    .de URLs

    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
    ä¸ĩè¾Ĩ
    -0.10
    æ´ĹåĩĢ
    -0.09
    ç¼ł
    -0.09
    å¼ĢåIJ¯äºĨ
    -0.09
    unan
    -0.09
    avan
    -0.09
    onal
    -0.09
    alive
    -0.09
    éĢĿ
    -0.09
    uhl
    -0.09
    POSITIVE LOGITS
    å¤ĸåĽ½
    0.08
    .meta
    0.08
    /meta
    0.08
    åįļè§Ī
    0.08
     meta
    0.07
     trib
    0.07
    ä¸Ģä¸Ģ
    0.07
    å¹Ħ
    0.07
    sole
    0.07
     bus
    0.07
    Activations Density 0.063%

    No Known Activations