© 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. 34529
    Prev
    Next
    INDEX
    Explanations

    climate change adaptation

    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
    缺éĻ·
    -0.10
    ä¸į顾
    -0.09
    çݯå¢ĥä¿ĿæĬ¤
    -0.09
    æ¼ķ
    -0.09
    è¿Ļæī¹
    -0.09
    鸡汤
    -0.09
     pros
    -0.08
    大è·Į
    -0.08
    æŨ
    -0.08
    å®
    -0.08
    POSITIVE LOGITS
    æłĩå¿ĹæĢ§
    0.09
    ä¸įåĨįæĺ¯
    0.09
    èĦĨ
    0.09
    èĦĨå¼±
    0.09
    Already
    0.09
     orderly
    0.09
    ä¸į说
    0.09
    ocalypse
    0.09
    æĹ¥æ¸IJ
    0.08
    æĿ¥ä¸įåıĬ
    0.08
    Activations Density 0.063%

    No Known Activations