© 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. 12189
    Prev
    Next
    INDEX
    Explanations

    orthodontic, orthopedics, orthodoxy

    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
    inning
    -0.10
    ç¬ijäºĨ
    -0.10
    ged
    -0.10
    强çĥĪçļĦ
    -0.10
    æĶ¿åºľéĥ¨éŨ
    -0.10
    AIM
    -0.09
    å²ij
    -0.09
     hứng
    -0.09
    aron
    -0.09
    hip
    -0.09
    POSITIVE LOGITS
    ogonal
    0.11
    oph
    0.11
     ngữ
    0.11
    ä¸įçĶ¨æĭħå¿ĥ
    0.10
    entic
    0.10
    -minded
    0.10
    odont
    0.09
    ìį¨
    0.09
    presso
    0.09
     minded
    0.08
    Activations Density 0.024%

    No Known Activations