© 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. 52497
    Prev
    Next
    INDEX
    Explanations

    notice or note something

    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
    åİļåİļ
    -0.10
    çłĿ
    -0.09
    éĶī
    -0.09
    oui
    -0.09
    è¯ķæİ¢
    -0.09
    座ä½į
    -0.09
    é»İ
    -0.09
    太ä¹ħ
    -0.09
    ospace
    -0.09
    æĪijçŁ¥éģĵ
    -0.09
    POSITIVE LOGITS
    注æĦıåĪ°
    0.13
     notice
    0.12
    notice
    0.12
     Notice
    0.11
    Notice
    0.10
     noticed
    0.10
    ä»Ķç»Ĩ
    0.10
    ç»Ĩå¿ĥ
    0.10
     Notices
    0.10
    .notice
    0.10
    Activations Density 0.069%

    No Known Activations