© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54293
    Prev
    Next
    INDEX
    Explanations

    interindividual pharmacokinetic variability

    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
    -ajax
    -0.09
    夸
    -0.09
    éĥĩ
    -0.09
    马
    -0.08
    é£İåħī
    -0.08
    æĽ¦
    -0.08
    åĭĸ
    -0.08
    ogie
    -0.08
    åİĨæŶ
    -0.08
    ä¸ĢçĻ¾å¤ļ
    -0.08
    POSITIVE LOGITS
    èį¯çī©
    0.12
    èIJĺ
    0.11
    ä¸Ģ身
    0.10
    drug
    0.10
    èĹ¥
    0.10
    interop
    0.09
     drug
    0.09
     drugs
    0.09
     Drug
    0.09
    Drug
    0.09
    Activations Density 0.605%

    No Known Activations