© 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. 64045
    Prev
    Next
    INDEX
    Explanations

    with [medical conditions/groups]

    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
    åĶ®ç¥¨
    -0.12
    å¾Ĺ罪
    -0.11
    éİı
    -0.11
    è¿Ļä¸ĢçĤ¹
    -0.10
    è¿ĻçĤ¹
    -0.10
    æ¢Ĩ
    -0.10
    éĦ¢
    -0.10
    æıī
    -0.10
    çİ«
    -0.10
    GRES
    -0.10
    POSITIVE LOGITS
     "
    0.07
    graph
    0.07
     mate
    0.07
    mate
    0.07
    çīµ
    0.06
     pa
    0.06
    RP
    0.06
     retro
    0.06
    ery
    0.06
    åıijå±ķ壮大
    0.06
    Activations Density 1.481%

    No Known Activations