© 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. 7062
    Prev
    Next
    INDEX
    Explanations

    professionals ending in -ian or -ist

    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
    odor
    -0.10
    anus
    -0.09
    xin
    -0.09
    书记
    -0.08
    thin
    -0.08
    shine
    -0.08
    è´
    -0.08
     Signs
    -0.08
    راد
    -0.08
    ниÑĨ
    -0.08
    POSITIVE LOGITS
    è¿Ļ个èģĮä¸ļ
    0.10
    å©Ĭ
    0.09
    çł»
    0.09
    ä¸Ģä¸ĸ
    0.09
    ê¹IJ
    0.09
    ä¿ij
    0.09
    æĪŁ
    0.08
    pus
    0.08
    iffs
    0.08
    åĪĨå·¥
    0.08
    Activations Density 0.013%

    No Known Activations