© 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. 20947
    Prev
    Next
    INDEX
    Explanations

    listen for or to

    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
    æįī
    -0.12
    å¤ļå¤ļ
    -0.09
    nik
    -0.09
    æĪª
    -0.09
    å®
    -0.09
    æĬ¹
    -0.09
    墨
    -0.08
    ä¸Ģæ³¢
    -0.08
    å¼Ī
    -0.08
    åij¨åĪĬ
    -0.08
    POSITIVE LOGITS
     listened
    0.12
    åĢ¾åIJ¬
    0.10
     listens
    0.10
     listen
    0.09
     Retreat
    0.09
    åIJ¬
    0.09
    izi
    0.09
    èģĨ
    0.09
    å½±åĵįåĬĽ
    0.09
    åIJ¬äºĨ
    0.09
    Activations Density 0.047%

    No Known Activations