© 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. 5297
    Prev
    Next
    INDEX
    Explanations

    in a... way

    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
    ters
    -0.11
    ç»´å°Ķ
    -0.09
    oping
    -0.09
    mit
    -0.09
    åīįæıIJæĺ¯
    -0.08
    çļĦäºĭå®ŀ
    -0.08
    éĢĴç»Ļ
    -0.08
    ç»Ŀ大å¤ļæķ°
    -0.08
    ç»Ħ建
    -0.08
    ãģ¾ãģ¾
    -0.08
    POSITIVE LOGITS
    æĹ¢èĥ½
    0.09
    ä¸Ģç§į
    0.09
    AndWait
    0.09
    çļĦæĸ¹å¼ı
    0.08
    æĸ¹å¼ı
    0.08
    çľ¼çļ®
    0.08
    çľĭäºĨä¸Ģ
    0.08
    anut
    0.08
    èݽ
    0.08
    æķ·
    0.08
    Activations Density 0.083%

    No Known Activations