© 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. 56545
    Prev
    Next
    INDEX
    Explanations

    electronically stored data

    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
    åĮ¹
    -0.11
     Bryant
    -0.09
    ç¥ŀä»Ļ
    -0.09
    åĭ¾
    -0.09
    знаÑĩ
    -0.08
    íĭĢ
    -0.08
    lexer
    -0.08
    å¼Ģåĩº
    -0.08
    виÑĤ
    -0.08
    纳
    -0.08
    POSITIVE LOGITS
    å¤ļç§įå½¢å¼ı
    0.11
    åħ¬åħ±èµĦæºIJ
    0.10
    æģ¯
    0.09
    浩
    0.09
     dean
    0.08
    æĢģ
    0.08
    没æľīåĬŀæ³ķ
    0.08
    tit
    0.08
    æĸĩåŃĹ
    0.08
    /board
    0.08
    Activations Density 0.125%

    No Known Activations