© 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. 7763
    Prev
    Next
    INDEX
    Explanations

    educational programs and awareness

    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
    享åıĹ
    -0.11
    ç¨Ģ
    -0.09
    è°ĥåīĤ
    -0.09
    åĬłå¿«å»ºè®¾
    -0.09
    okin
    -0.09
    绣çŃ¹æİ¨è¿Ľ
    -0.08
    读书
    -0.08
    åĨ³èĥľ
    -0.08
    åĩĨ
    -0.08
    追éĢIJ
    -0.08
    POSITIVE LOGITS
    éĺ²æ²»
    0.12
    é¢Ħéĺ²
    0.11
    å¯ĵ
    0.11
    éĺ²èĮĥ
    0.10
    å®£ä¼łæķĻèĤ²
    0.10
    aware
    0.10
    å¢ŀ设
    0.10
    综åIJĪæ²»çIJĨ
    0.09
    è¯Ŀåī§
    0.09
     awareness
    0.09
    Activations Density 0.107%

    No Known Activations