© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10476
    Prev
    Next
    INDEX
    Explanations

    placeholders in code/paths

    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
     Hubbard
    -0.09
     surfaces
    -0.08
    è¡Ĺä¸Ĭ
    -0.08
    (("
    -0.08
    æİīäºĨ
    -0.08
    æĻ®åıĬ
    -0.08
     бÑĥкв
    -0.08
    .onCreate
    -0.08
    .addProperty
    -0.08
    GREE
    -0.08
    POSITIVE LOGITS
    SelectionMode
    0.10
    å±ŀäºİèĩªå·±
    0.10
    èĩªå·±çļĦ
    0.10
    æīĭä¸ŃçļĦ
    0.09
    æĺ¯è°ģ
    0.09
    è¿Ļ个åIJįåŃĹ
    0.09
    ä¸Ģ个æĺŁæľŁ
    0.09
     tên
    0.09
    æģ¶éŃĶ
    0.08
    身躯
    0.08
    Activations Density 0.405%

    No Known Activations