© 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. 9061
    Prev
    Next
    INDEX
    Explanations

    English translation

    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
    æµ·å¤ĸ
    -0.18
    å¤ĸåĽ½äºº
    -0.16
    åĽ½å¤ĸ
    -0.16
    åĩºåĽ½
    -0.15
    å¤ĸåĽ½
    -0.14
     overseas
    -0.14
    åĽŀåĽ½
    -0.14
    å¤ĸç±į
    -0.14
     иноÑģÑĤÑĢан
    -0.14
     foreign
    -0.13
    POSITIVE LOGITS
    ä¸įæĺĵ
    0.10
    ä¹ĭ声
    0.09
    éŨæĪ·ç½ijç«Ļ
    0.09
    羣å®ŀæĢ§
    0.08
    è¡¡éĺ³
    0.08
    mal
    0.08
    ÑĭÑħ
    0.08
    羯
    0.08
     Laud
    0.08
    å®ĺæĸ¹å¾®ä¿¡
    0.08
    Activations Density 0.111%

    No Known Activations