© 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. 52212
    Prev
    Next
    INDEX
    Explanations

    as [role/function]

    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
    åºĶçĶ¨
    -0.09
    æľīçĶ¨
    -0.09
    让人
    -0.09
    alian
    -0.09
    verts
    -0.09
    åĪ©äºİ
    -0.09
    èİĺ
    -0.08
    è¿IJçĶ¨
    -0.08
     Shack
    -0.08
    幸
    -0.08
    POSITIVE LOGITS
    驱
    0.11
    åĪĩåħ¥çĤ¹
    0.10
     Ñģвое
    0.10
    æŁ¯
    0.09
    溶
    0.09
    æĪij没æľī
    0.09
    å±ıéļľ
    0.09
    æĸ¡
    0.09
    çŃ¹çłģ
    0.09
    åĸĭ
    0.09
    Activations Density 0.107%

    No Known Activations