© 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. 17638
    Prev
    Next
    INDEX
    Explanations

    in our lives

    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
    çıŃéķ¿
    -0.09
    è¿Ļå¥Ĺ
    -0.09
    ä¸ĢåıĮ
    -0.08
    fur
    -0.08
    éĻ·
    -0.08
    åijĬè¯ī大家
    -0.08
    èĵ¬
    -0.08
     fours
    -0.08
     Closure
    -0.08
    å°¤
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»
    0.13
     ØŃÙĬاتÙĩ
    0.12
    çĶŁæ´»çļĦ
    0.12
    人çĶŁ
    0.12
     life
    0.12
    çļĦçĶŁæ´»
    0.11
    çļĦ人çĶŁ
    0.11
    çĶŁæ´»ä¸Ń
    0.11
     ØŃÙĬات
    0.11
    çĶŁåij½
    0.11
    Activations Density 0.102%

    No Known Activations