© 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. 58267
    Prev
    Next
    INDEX
    Explanations

    medical graduates and residency

    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
    çĪ¶åŃIJ
    -0.09
     esk
    -0.09
    å·´æĭī
    -0.09
    ãĤĤãĤĬ
    -0.08
     Beng
    -0.08
    _elt
    -0.08
    club
    -0.08
    ActionResult
    -0.08
    guard
    -0.08
    å¤į
    -0.08
    POSITIVE LOGITS
    æī§ä¸ļ
    0.13
    è¯ŀ
    0.11
    åĮ»å¸Ī
    0.10
    é£ŀè¡Įåijĺ
    0.10
    åŁ¹åħ»åѦçĶŁ
    0.10
    åѦçĶŁçļĦ
    0.10
    æł¸å¿ĥåĮº
    0.10
    æ¯ķä¸ļçĶŁ
    0.09
    åĬ©çIJĨ
    0.09
    å®ŀä¹ł
    0.09
    Activations Density 0.225%

    No Known Activations