© 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. 32228
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical interventions

    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
    stell
    -0.11
    ä¸īåĽĽ
    -0.09
    é£ŀæī¬
    -0.09
    fit
    -0.09
    主ä¹īæĢĿæĥ³
    -0.09
    OfFile
    -0.09
    chaft
    -0.09
     Isle
    -0.09
    å¥ij
    -0.09
    éķ¿å®ī
    -0.09
    POSITIVE LOGITS
    -grade
    0.12
    è¡Įä¸ļçļĦ
    0.09
    anson
    0.09
    çķĮ
    0.09
    cing
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    ishing
    0.09
    åħ¬åı¸çļĦ
    0.09
    ysics
    0.09
     phẩm
    0.09
    Activations Density 0.022%

    No Known Activations