© 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. 7427
    Prev
    Next
    INDEX
    Explanations

    giving to them

    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
    æľ¬ç«Ļ
    -0.11
    éĢĤåIJĪèĩªå·±
    -0.09
    为èĩªå·±
    -0.08
    GRAM
    -0.08
    Own
    -0.08
    æĹ¥æľ¬ãģ®
    -0.08
    没æľīå¿ħè¦ģ
    -0.08
    .cal
    -0.08
    ä¸Ģåıª
    -0.08
    alysis
    -0.08
    POSITIVE LOGITS
    ä»ĸ们
    0.43
    ä»ĸä»¬åľ¨
    0.42
    ä»ĸ们çļĦ
    0.41
    她们
    0.36
    ä»ĸ们æĺ¯
    0.35
    ä»ĸåĢij
    0.35
    å®ĥ们
    0.35
    让ä»ĸ们
    0.33
    ä»ĸ们ä¼ļ
    0.33
    å½¼ãĤī
    0.32
    Activations Density 0.442%

    No Known Activations