© 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. 50134
    Prev
    Next
    INDEX
    Explanations

    historical and political change

    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
    追踪
    -0.09
    æĬ¬
    -0.09
    ä¼łéĹ»
    -0.09
    缴æݥ影åĵį
    -0.08
    人家
    -0.08
    å¸ĤæķĻèĤ²å±Ģ
    -0.08
    æĸĭ
    -0.08
    è¡Įä¸ļåĨħ
    -0.08
    æµ®åĬ¨
    -0.08
     köln
    -0.08
    POSITIVE LOGITS
    åIJĦåĽ½
    0.11
    åħ¶ä»ĸåĽ½å®¶
    0.10
    åľ¨è¿ĩ渡
    0.10
    åİĨåı²
    0.10
     elect
    0.09
     ìĹŃìĤ¬
    0.09
    ç»Łæ²»
    0.09
    5
    0.09
     transition
    0.09
    宪
    0.09
    Activations Density 0.123%

    No Known Activations