© 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. 17623
    Prev
    Next
    INDEX
    Explanations

    journalist reporting or creating

    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
    ä»ĸä»¬åľ¨
    -0.09
    å½ĵå±Ģ
    -0.09
    ILES
    -0.09
    ä»ĸ们ä¼ļ
    -0.09
    liers
    -0.09
    åĽłä¸ºä»ĸ们
    -0.08
     Usage
    -0.08
    ImageContext
    -0.08
    æīĢæľīæĥħèĬĤ
    -0.08
    æľĽåİ»
    -0.08
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.11
    åĬłåħ¥äºĨ
    0.09
    ainer
    0.09
    éĹ»åIJį
    0.09
    èµ·äºĨ
    0.09
    被认为æĺ¯
    0.08
    çĭ¬
    0.08
    鬯
    0.08
    ä¸ĭäºĨ
    0.08
    ги
    0.08
    Activations Density 0.163%

    No Known Activations