© 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. 53074
    Prev
    Next
    INDEX
    Explanations

    conference centers

    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
    é¢ł
    -0.11
    åħ³éŨ
    -0.09
    ëįķ
    -0.09
    åİĿ
    -0.09
    agens
    -0.09
    çī
    -0.08
    大è±Ĩ
    -0.08
    bach
    -0.08
    lac
    -0.08
     transc
    -0.08
    POSITIVE LOGITS
    æĭĨ
    0.11
    åĿ¼
    0.11
    ä¼ļ议室
    0.11
    íļĮìĿĺ
    0.10
    ä¼ļè®®
    0.09
    æľĥèŃ°
    0.09
    å®´
    0.09
    æīĪ
    0.09
    ä¼ļå½±åĵįåĪ°
    0.09
     conference
    0.09
    Activations Density 0.100%

    No Known Activations