© 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. 2575
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    rint
    -0.11
    öst
    -0.10
    计åĪĴçĶŁèĤ²
    -0.09
    沧
    -0.09
    姣
    -0.09
    .Dispatcher
    -0.09
    Drawable
    -0.08
    æĭŃ
    -0.08
    æıĸ
    -0.08
    ahan
    -0.08
    POSITIVE LOGITS
    æĸĩ件
    0.14
     file
    0.12
     files
    0.12
     ÑĦайл
    0.11
     (*.
    0.10
    ç®´
    0.10
    æł¼å¼ı
    0.10
     Files
    0.10
     ÑĦайла
    0.09
    ãĥķãĤ¡ãĤ¤ãĥ«
    0.09
    Activations Density 0.242%

    No Known Activations