© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38302
    Prev
    Next
    INDEX
    Explanations

    Tea Party, Sarah Palin, CoffeeScript

    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
    Intl
    -0.11
    ä¸ļä½Ļ
    -0.10
    åĦ¿
    -0.10
    çļĦçľ¼åħī
    -0.10
    Thunk
    -0.10
    æ·Ŀ
    -0.10
    çļĦçľ¼ç¥ŀ
    -0.09
    çļĦä¼ģä¸ļ
    -0.09
    çļĦèģĮä¸ļ
    -0.09
     chân
    -0.09
    POSITIVE LOGITS
    çĵ¢
    0.09
    rien
    0.08
     Lazar
    0.08
    äºĽä»Ģä¹Ī
    0.08
    stry
    0.08
    ãģ»ãģĨ
    0.08
    2
    0.08
    .mx
    0.07
    çĽı
    0.07
    对èĩªå·±
    0.07
    Activations Density 0.002%

    No Known Activations