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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36417
    Prev
    Next
    INDEX
    Explanations

    science and history of medicine

    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
    äºĨä»ĸçļĦ
    -0.10
    èĻļ
    -0.09
    æĬĵç´§
    -0.09
    æ²Ĩ
    -0.09
    å¼Ģåı£
    -0.09
    èĻĽ
    -0.09
    çļĦçľ¼ç¥ŀ
    -0.08
    ç»ĻåĪ«äºº
    -0.08
    åIJŃ
    -0.08
    éĥ§
    -0.08
    POSITIVE LOGITS
    ç§ijæĻ®
    0.12
    ç§ijåįı
    0.11
    science
    0.11
    ç§ijåŃ¦å®¶
    0.11
     science
    0.10
     scientists
    0.09
     Science
    0.09
     crunch
    0.08
    Science
    0.08
    STS
    0.08
    Activations Density 0.072%

    No Known Activations