© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5431
    Prev
    Next
    INDEX
    Explanations

    conference and expo events

    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
     Blair
    -0.09
    è´Ŀå°Ķ
    -0.09
    æľ¬åħ¬åı¸
    -0.09
    æİī
    -0.08
     Studio
    -0.08
    å·¥ä½ľå®¤
    -0.08
     studio
    -0.08
    ycl
    -0.08
    éĶ¦
    -0.08
    禮
    -0.08
    POSITIVE LOGITS
    ä¼ļè®®ä¸Ĭ
    0.15
    大ä¼ļä¸Ĭ
    0.15
    大ä¼ļ
    0.12
    ä¼ļä¸Ĭ
    0.11
     conference
    0.11
    第äºĶå±Ĭ
    0.11
     expo
    0.10
    第äºĮå±Ĭ
    0.10
    ä¼ļè®®
    0.10
    ä¸Ģå¹´ä¸Ģ度
    0.10
    Activations Density 0.130%

    No Known Activations