© 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. 35162
    Prev
    Next
    INDEX
    Explanations

    ending punctuation or common conjunctions

    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
    éĿŀ常çļĦ
    -0.10
    é£İæ°Ķ
    -0.10
    说ä¸įåĩº
    -0.09
    éĤ£æł·çļĦ
    -0.09
    éĿŀ常åĸľæ¬¢
    -0.09
    æĥħåĨµè¿Ľè¡Į
    -0.09
    è¿Ļåĩłä¸ª
    -0.09
    æĺ¯éĿŀ常
    -0.09
    ä¸įè¿ĩ
    -0.09
    è¿ĺæĺ¯å¾Ī
    -0.09
    POSITIVE LOGITS
    ãģłãģĹ
    0.13
    çĶļèĩ³
    0.13
    ãģ§ãģĻãģĹ
    0.11
    èĢĮä¸Ķ
    0.10
    æľīçļĦ
    0.10
     GRA
    0.09
    หมà¸Ķ
    0.09
    çŃīçŃī
    0.09
     promot
    0.08
    even
    0.08
    Activations Density 0.177%

    No Known Activations