© 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. 33122
    Prev
    Next
    INDEX
    Explanations

    to ... moderate, to ... reduce

    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
    ä¸Ģå®ļç¨ĭ度
    -0.11
     Ñģка
    -0.10
    符
    -0.09
    ield
    -0.09
    æݳ
    -0.08
    èĪį
    -0.08
    çĪ¬
    -0.08
    çĸijæĥij
    -0.08
    rated
    -0.08
    åĪ¸
    -0.08
    POSITIVE LOGITS
    vir
    0.10
     DOS
    0.09
    å§Ĭ妹
    0.09
    空åĨĽ
    0.09
    说ä»Ģä¹Ī
    0.08
    Dos
    0.08
     vir
    0.08
    èİ«è¿ĩäºİ
    0.08
    اذ
    0.08
    æĮ½åĽŀ
    0.08
    Activations Density 0.029%

    No Known Activations