© 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. 51316
    Prev
    Next
    INDEX
    Explanations

    hot and humid weather

    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
    æļĿ
    -0.11
    èĢĻ
    -0.10
    æĬĦè¢Ń
    -0.10
    éĵ§
    -0.10
    çŀij
    -0.09
    éĻª
    -0.09
    æ¤IJ
    -0.09
    éħįå¥Ĺ
    -0.09
    æģŃ
    -0.09
    rijk
    -0.09
    POSITIVE LOGITS
    æļij
    0.24
    å¤ıåŃ£
    0.20
    å¤ıæĹ¥
    0.20
    çĤİçĥŃ
    0.19
    å¤ı天
    0.18
    æļijæľŁ
    0.18
     summer
    0.17
    溽
    0.17
    æ±Ĺ
    0.14
    çĤİ
    0.14
    Activations Density 0.091%

    No Known Activations