© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37506
    Prev
    Next
    INDEX
    Explanations

    astronomical observations, models predict

    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
    æĬ½
    -0.09
     rum
    -0.08
    åĢ¼å¾Ĺä¸Ģ
    -0.08
    æĸ¹å¼ıè¿Ľè¡Į
    -0.08
    ä¸įåħ¬å¹³
    -0.08
    æĸŁ
    -0.08
    æĹłå¿§
    -0.08
     каÑĩ
    -0.08
    olini
    -0.08
     ÑģÑĥд
    -0.08
    POSITIVE LOGITS
    /models
    0.09
    æľĢæĸ°çļĦ
    0.09
    (models
    0.09
    ERM
    0.09
    é¹ħ
    0.09
     fals
    0.08
    åĢĴ
    0.08
    åºŁå¼ĥ
    0.08
    çĥŁèĬ±
    0.08
    åħīçħ§
    0.08
    Activations Density 0.280%

    No Known Activations