© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8308
    Prev
    Next
    INDEX
    Explanations

    fetal and prenatal conditions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æŀ£
    -0.09
    wolf
    -0.08
     forks
    -0.08
     burned
    -0.08
     burns
    -0.08
     hor
    -0.08
    _px
    -0.07
    .dr
    -0.07
    imi
    -0.07
    ç»´æĮģ
    -0.07
    POSITIVE LOGITS
    èĥİåĦ¿
    0.15
     unborn
    0.14
    èĥİ
    0.14
    æµģ产
    0.12
    éĽ
    0.11
    åľ¨éĩĮéĿ¢
    0.11
    åŃķèĤ²
    0.11
    å¨ł
    0.10
    åŃķ
    0.10
     внÑĥÑĤÑĢи
    0.10
    Activations Density 0.270%

    No Known Activations