© 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. 39374
    Prev
    Next
    INDEX
    Explanations

    Veterans Affairs and Health Administration

    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
    ocracy
    -0.09
    缴纳
    -0.08
    å¥ijæľº
    -0.08
    éĢĤ
    -0.08
    家
    -0.08
    å±ħæ°ij
    -0.08
    åĮĹ约
    -0.08
     Ney
    -0.08
     <->
    -0.08
    esa
    -0.08
    POSITIVE LOGITS
    ASTER
    0.09
    çļĦä¸ľè¥¿
    0.09
     Burns
    0.09
    ä¸ľè¥¿
    0.09
    ç½²
    0.09
     Hairst
    0.09
    çļĦäºĭæĥħ
    0.09
    积æ·Ģ
    0.08
    ariat
    0.08
    elled
    0.08
    Activations Density 0.012%

    No Known Activations