© 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. 18383
    Prev
    Next
    INDEX
    Explanations

    Medicare, patients, nursing, facility

    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
     donor
    -0.09
     Ferguson
    -0.09
    ä¾Ľè´§
    -0.08
    æľīåºıæİ¨è¿Ľ
    -0.08
    åĩī
    -0.08
    utive
    -0.08
     donors
    -0.08
    大ä¼ļ
    -0.08
    _blocked
    -0.08
     Jersey
    -0.08
    POSITIVE LOGITS
     Responsibility
    0.09
    è¢
    0.09
    aday
    0.09
    滥
    0.08
    Framework
    0.08
     cushions
    0.08
    Pad
    0.08
    cstdio
    0.08
     вÑģ
    0.08
     gol
    0.08
    Activations Density 0.163%

    No Known Activations