© 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. 20672
    Prev
    Next
    INDEX
    Explanations

    administrative support or assistance

    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
    æī§æķĻ
    -0.14
    å¸ĪèµĦ
    -0.13
    åģ¿
    -0.11
    讲课
    -0.10
    宣讲
    -0.10
    alion
    -0.10
    讲å¸Ī
    -0.09
    çĹĽ
    -0.09
    éħ¿éħĴ
    -0.09
    èģĺ请
    -0.09
    POSITIVE LOGITS
    7
    0.11
    4
    0.11
    0
    0.11
    6
    0.10
    8
    0.10
    9
    0.10
    5
    0.10
    2
    0.10
    3
    0.10
    æİ¥å¾ħ
    0.09
    Activations Density 0.061%

    No Known Activations