© 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. 47520
    Prev
    Next
    INDEX
    Explanations

    pemphigus, varicella, echinococcus

    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
    æŀŀ
    -0.10
    onna
    -0.10
     Panama
    -0.09
    缮çļĦåľ¨äºİ
    -0.09
     McKenzie
    -0.08
    IELD
    -0.08
    ppard
    -0.08
    éĥ½æľīèĩªå·±
    -0.08
    åįģåŃĹ
    -0.08
     ark
    -0.08
    POSITIVE LOGITS
    rum
    0.09
    .asp
    0.09
    ä»°
    0.09
    ego
    0.08
    ÙĤÙĨ
    0.08
    igli
    0.08
    NBC
    0.08
    å¯Ĥ
    0.08
    PROTO
    0.08
    ä¸ĢèĤ¡
    0.08
    Activations Density 0.170%

    No Known Activations