© 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. 5208
    Prev
    Next
    INDEX
    Explanations

    leadership teams

    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
    主è§Ĥ
    -0.10
    èħ»
    -0.09
    å´ĩæĭľ
    -0.09
    çĽij
    -0.09
    å¼¹
    -0.08
     Pri
    -0.08
    CLS
    -0.08
    æĺĻ
    -0.08
    åįİ缼
    -0.08
    INAL
    -0.08
    POSITIVE LOGITS
    otron
    0.11
    å®ŀå¹²
    0.10
    é¢Ĩ导èĢħ
    0.09
    åĽ½æľīä¼ģä¸ļ
    0.09
    åģļ人
    0.09
    .chart
    0.09
    åĸĦæĦı
    0.09
    åĴĮ个人
    0.09
    åĽ¢éĺŁ
    0.09
     leader
    0.09
    Activations Density 0.127%

    No Known Activations