© 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. 50970
    Prev
    Next
    INDEX
    Explanations

    missionaries and evangelicals

    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
    çļĦåŃ¦ä¹ł
    -0.10
    ä¸Ģå¥Ĺ
    -0.10
    éĢļè¡Įè¯ģ
    -0.09
    åĵį
    -0.09
    å½ĵä¹ĭ
    -0.09
    _CRC
    -0.08
    mium
    -0.08
    moz
    -0.08
    æ¶ī
    -0.08
    éĩĬ
    -0.08
    POSITIVE LOGITS
    orient
    0.09
    å·¥ä½ľçļĦ
    0.08
    æ´»åĬ¨ä¸Ń
    0.08
     Beit
    0.08
    pell
    0.08
     tar
    0.08
    éħµ
    0.08
    å¥
    0.08
    æīĵä»Ĺ
    0.08
     Olsen
    0.08
    Activations Density 0.015%

    No Known Activations