© 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. 49293
    Prev
    Next
    INDEX
    Explanations

    activities and hobbies

    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
    iani
    -0.09
    å®
    -0.08
    æķķ
    -0.08
     Simmons
    -0.08
    ä¹Ķ
    -0.08
    enk
    -0.08
    æĿĸ
    -0.08
    æĥĬå¥ĩ
    -0.08
    æĬ¤å£«
    -0.08
     episode
    -0.08
    POSITIVE LOGITS
    æīĵ交éģĵ
    0.09
    éºĴ
    0.09
    åı°ä¸Ĭ
    0.09
    å·¥ä½ľä¸Ń
    0.09
    è¿Ļ个èģĮä¸ļ
    0.09
    éĥ¨åī¯
    0.09
    æ¶ķ
    0.09
    主ä¸ļ
    0.08
    çļĦæĦ¿æľĽ
    0.08
    è¿Ļ个è¡Įä¸ļ
    0.08
    Activations Density 0.143%

    No Known Activations