© 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. 32830
    Prev
    Next
    INDEX
    Explanations

    demand payment or else

    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
    Rem
    -0.09
    éľ¹
    -0.09
    ages
    -0.08
    unken
    -0.08
    é¼ĵèĪŀ
    -0.08
    rome
    -0.08
    å¤ĸ交
    -0.08
    æĶ¶ç´§
    -0.08
    æĤĦçĦ¶
    -0.08
     Grimm
    -0.08
    POSITIVE LOGITS
    帮ä»ĸ
    0.11
    ioc
    0.10
    æĺİ天
    0.09
    èIJ
    0.09
    ç«ĭåĪ»
    0.09
    éĺħ读åħ¨æĸĩ
    0.09
    ãĥ¼ãĥ³
    0.09
    娶
    0.09
     beste
    0.09
     Bak
    0.08
    Activations Density 0.051%

    No Known Activations