© 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. 62035
    Prev
    Next
    INDEX
    Explanations

    nonsteroidal anti-inflammatory 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
    iets
    -0.09
    _conversion
    -0.09
    oho
    -0.09
    éľģ
    -0.09
    agraph
    -0.09
    åĬ¨æijĩ
    -0.09
    моÑĢ
    -0.09
     Wire
    -0.09
    èµĶ
    -0.08
    èĪĮ头
    -0.08
    POSITIVE LOGITS
     aspir
    0.10
    åĥįãģį
    0.09
     brand
    0.09
    anuts
    0.09
    æįı
    0.09
    头çĸ¼
    0.08
    è§ī
    0.08
    çļĦåħ·ä½ĵ
    0.08
     Stein
    0.08
     sidew
    0.08
    Activations Density 0.116%

    No Known Activations