© 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. 22637
    Prev
    Next
    INDEX
    Explanations

    new pharmacologic or diagnostic methods

    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
    åIJĦç§įåIJĦæł·
    -0.10
    åĴ©
    -0.09
    次ä¼ļè®®
    -0.09
    ä¸Ģç³»åĪĹ
    -0.09
    éĤ£ç§į
    -0.08
    èĪĶ
    -0.08
    è¿Ļç±»
    -0.08
    åŬ
    -0.08
    èĪIJ
    -0.08
    çłĶ究表æĺİ
    -0.08
    POSITIVE LOGITS
     revis
    0.10
    [J
    0.09
    åĪį
    0.08
    åıĬåħ¶
    0.08
    éĩİ
    0.08
    ÑĪин
    0.08
    äºĮ次
    0.08
    çī¢
    0.08
    _pull
    0.07
    çļĩ
    0.07
    Activations Density 3.882%

    No Known Activations