© 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. 1525
    Prev
    Next
    INDEX
    Explanations

    randomized clinical trials studies

    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
    æ´Ĵ
    -0.10
    itech
    -0.09
     SOM
    -0.09
    åı£åı·
    -0.09
    eling
    -0.08
    ä¸ĵèģĮ
    -0.08
    _framework
    -0.08
    pf
    -0.08
    -gun
    -0.08
    lay
    -0.08
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.15
     studies
    0.13
    嶷
    0.10
     study
    0.10
     trails
    0.09
    è¿Ļåľº
    0.09
    è¯ķéªĮ
    0.09
     Studies
    0.09
    è°ĥæŁ¥æĺ¾ç¤º
    0.09
    è¾¾ä¸įåĪ°
    0.09
    Activations Density 0.493%

    No Known Activations