© 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. 33665
    Prev
    Next
    INDEX
    Explanations

    medication and prescribed drugs

    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
    _framework
    -0.10
    å·¢
    -0.09
    ilon
    -0.09
    igel
    -0.09
    ittal
    -0.09
    æįŁ
    -0.09
    _extend
    -0.09
    urve
    -0.09
     Hire
    -0.09
    注åĨĮèµĦæľ¬
    -0.09
    POSITIVE LOGITS
     medications
    0.11
    sth
    0.09
     medication
    0.09
    æļ®
    0.09
     prescribed
    0.08
    çĵľ
    0.08
    å§ij
    0.08
    å®īå®ļ
    0.08
    èį¯åĵģ
    0.08
    æĺ¯ä»Ģä¹Īåij¢
    0.08
    Activations Density 0.129%

    No Known Activations