© 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. 53502
    Prev
    Next
    INDEX
    Explanations

    money and salaries

    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
    深交
    -0.09
    å¼Ģåľº
    -0.09
    marshall
    -0.09
    鸳
    -0.09
    stra
    -0.08
    ä¸Ģè½®
    -0.08
    .slim
    -0.08
    é¢Ĥ
    -0.08
    curring
    -0.08
    OFFSET
    -0.08
    POSITIVE LOGITS
    çļĦèģĮä¸ļ
    0.11
    éħ¬
    0.10
    äºĨä»ĸçļĦ
    0.10
    èĸªæ°´
    0.10
    å¾ħéģĩ
    0.10
    èĸªéħ¬
    0.09
    æŃ»åIJİ
    0.09
    çŃ¾ä¸ĭ
    0.09
    ä¸įæŃ¢
    0.09
    æķķ
    0.09
    Activations Density 0.041%

    No Known Activations