© 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. 58424
    Prev
    Next
    INDEX
    Explanations

    redefine or redefine 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
    .rl
    -0.10
    Advisor
    -0.09
    VML
    -0.09
    å½Ĺ
    -0.09
    allen
    -0.08
    ãģĭãģĦ
    -0.08
    ä¸Ģå®ļ
    -0.08
    è¿IJè´¹
    -0.08
    ops
    -0.08
    èī²è°ĥ
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåı«
    0.16
    ä»Ģä¹Īæĺ¯
    0.14
    è¦ģåģļ
    0.10
    åºĶæľīçļĦ
    0.10
    ä»Ģä¹Īäºĭ
    0.10
    平稳
    0.10
    è¦ģä¸įè¦ģ
    0.09
    æĿĤè´¨
    0.09
    åģļ强
    0.09
    .assertTrue
    0.09
    Activations Density 0.029%

    No Known Activations