© 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. 1941
    Prev
    Next
    INDEX
    Explanations

    notify or inform

    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
     Kushner
    -0.10
    pend
    -0.09
     Cheney
    -0.09
    oÅĽci
    -0.08
    ivre
    -0.08
    è¯ķæİ¢
    -0.08
    .Dependency
    -0.08
    åīĮ
    -0.08
    licated
    -0.08
     luder
    -0.08
    POSITIVE LOGITS
    对åºĶçļĦ
    0.10
    主管éĥ¨éŨ
    0.10
    è¦ģç´§
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    诸å¦Ĥ
    0.09
     Eaton
    0.09
    åij¨åĽ´çļĦ
    0.08
    讲课
    0.08
    æīĢåľ¨çļĦ
    0.08
    ãĤ¦ãĤ©ãĥ¼
    0.08
    Activations Density 0.017%

    No Known Activations