© 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. 12410
    Prev
    Next
    INDEX
    Explanations

    dubbed or coined

    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
    enia
    -0.09
    APS
    -0.09
    ä¸įäºĨ
    -0.08
    HING
    -0.08
    ored
    -0.08
    owers
    -0.08
    é¦
    -0.08
    onnement
    -0.08
    å¤ļäºĨ
    -0.08
    ãİĿ
    -0.08
    POSITIVE LOGITS
    èĢĮæĪIJ
    0.11
    eer
    0.09
    ../../../
    0.09
    illary
    0.09
    aires
    0.09
    åħ½
    0.09
    lesh
    0.09
    çĺ¸
    0.09
    XXXXXXXX
    0.09
    ght
    0.09
    Activations Density 0.012%

    No Known Activations