© 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. 9266
    Prev
    Next
    INDEX
    Explanations

    Alaska and place names

    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
    æ¼ī
    -0.10
    åijĽ
    -0.08
    anon
    -0.08
    å¸ĮæľĽå¤§å®¶
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    ICI
    -0.08
    ä¹Łä¸įåı¯èĥ½
    -0.08
    ä»ĸåľ¨
    -0.08
    ä¸IJ
    -0.08
    åı¦æľī
    -0.08
    POSITIVE LOGITS
     competing
    0.09
    ä¿Ħ
    0.09
    ä»ĩ
    0.09
    ТЬ
    0.09
    ç¡IJ
    0.09
    å°ĸ
    0.08
    _caption
    0.08
    Russian
    0.08
    æ´ª
    0.08
    èĭıèģĶ
    0.08
    Activations Density 0.029%

    No Known Activations