© 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. 55299
    Prev
    Next
    INDEX
    Explanations

    always + common following words

    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
    ä¸ĢçĤ¹åĦ¿
    -0.09
    ä¸Ģè·¯ä¸Ĭ
    -0.09
    åĪĨæĪIJ
    -0.08
    åģıåģı
    -0.08
     loc
    -0.08
    åĪļ好
    -0.08
    BILL
    -0.08
    ç»ĪçĶŁ
    -0.08
    æķ´å¤©
    -0.08
    urma
    -0.08
    POSITIVE LOGITS
    éĥ½ä¼ļæľī
    0.10
    ä¸Ģè½®
    0.10
    uds
    0.10
    ç²½
    0.10
    -ton
    0.09
    çªĴ
    0.09
    engo
    0.09
    缼ä¸ĸ
    0.09
    éĥ½ä¸įä¼ļ
    0.08
    éĥ½æľĥ
    0.08
    Activations Density 0.030%

    No Known Activations