© 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. 31118
    Prev
    Next
    INDEX
    Explanations

    phrases and questions using "do"

    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
    é£İåIJ¹
    -0.11
     Ella
    -0.09
    ãĥīãĥ«
    -0.09
    Õº
    -0.09
    è§ģè¯ģ
    -0.09
    ır
    -0.09
    _GP
    -0.09
    æīĵçĿĢ
    -0.09
    åı¦æľī
    -0.09
    ÙħÙĪÙĨ
    -0.09
    POSITIVE LOGITS
    ied
    0.09
    sst
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    ç½ij讯
    0.09
    gne
    0.09
    ava
    0.09
    èħ»
    0.09
    ä»Ģä¹Īæł·
    0.08
    åģĩåĨĴ
    0.08
    å¼Ħå¾Ĺ
    0.08
    Activations Density 0.079%

    No Known Activations