© 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. 30266
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    ãģ¾ãģļ
    -0.11
    æĹ¢æĺ¯
    -0.11
    é¦ĸåħĪ
    -0.10
    æŀľçĦ¶
    -0.09
    严èĤĥ
    -0.09
     both
    -0.09
    åİŁæłĩé¢ĺ
    -0.09
    æĹ¢åı¯ä»¥
    -0.08
    ä¸įçŁ¥ä¸įè§ī
    -0.08
    æĹ¢è¦ģ
    -0.08
    POSITIVE LOGITS
    èĢĮæĿ¥
    0.11
    é«ĺäºİ
    0.11
    åħ¶ä¸Ń
    0.11
    è¿Ļåħ¶ä¸Ń
    0.10
    è¿ĻæĦıåij³çĿĢ
    0.10
    åħ¶ä¸ŃåĮħæĭ¬
    0.10
    åħ¶ä¸Ńæľī
    0.10
     пÑĢиÑĩ
    0.09
    åIJĮæľŁ
    0.09
    åı¦ä¸ĢåįĬ
    0.09
    Activations Density 0.214%

    No Known Activations