© 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. 12054
    Prev
    Next
    INDEX
    Explanations

    materialization from a process

    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
    鼩
    -0.09
    ãĥ¼ãĤº
    -0.09
    è°ģçŁ¥
    -0.09
    è¿Ļæł·åģļ
    -0.08
    éĴ§
    -0.08
    æѤæŶ
    -0.08
    åIJĮæľŁ
    -0.08
    umm
    -0.08
    ึà¸ĩ
    -0.08
    able
    -0.08
    POSITIVE LOGITS
     дела
    0.10
    ÑģÑĤавка
    0.08
     Investigations
    0.08
    è¦ģåİ»
    0.08
    丰å¯Į
    0.08
    forth
    0.08
    dpi
    0.08
     ÑħоÑĤÑĮ
    0.08
    nü
    0.08
    ű
    0.08
    Activations Density 0.035%

    No Known Activations