© 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. 8232
    Prev
    Next
    INDEX
    Explanations

    already specified

    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
    ä¸Ŀ毫
    -0.09
    åĿij
    -0.09
    说æĺ¯
    -0.08
    宵
    -0.08
    -Sah
    -0.08
    çĥŁèĬ±
    -0.08
    å°Ŀè¯ķ
    -0.08
    arro
    -0.08
    åĪ®
    -0.08
    vecs
    -0.08
    POSITIVE LOGITS
    already
    0.22
     already
    0.22
    ä¸įéľĢè¦ģ
    0.20
    å·²ç»ıæľī
    0.19
    Already
    0.19
     Already
    0.19
    æľ¬èº«å°±
    0.19
    å·²ç»ıæľīäºĨ
    0.18
    æĹłéľĢ
    0.17
    åı¯ä»¥çĽ´æİ¥
    0.17
    Activations Density 0.297%

    No Known Activations