© 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. 12393
    Prev
    Next
    INDEX
    Explanations

    medical referrals and levels of care

    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
    åĨ»
    -0.10
    atus
    -0.09
     Morg
    -0.09
    .getItemId
    -0.09
    .mixin
    -0.09
    quate
    -0.09
    gn
    -0.09
    èį·
    -0.09
    ç´IJ
    -0.09
    atform
    -0.09
    POSITIVE LOGITS
    翼
    0.12
    ä¸į失
    0.12
    çĸij
    0.10
    çĸijä¼¼
    0.09
    转ä¼ļ
    0.09
    tee
    0.09
    å¿ħè¦ģ
    0.09
    åģļ强
    0.09
    éĢģå¾Ģ
    0.09
    çĸijéĹ®
    0.09
    Activations Density 0.299%

    No Known Activations