© 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. 28104
    Prev
    Next
    INDEX
    Explanations

    lap, complacency, glory, back, fabrication

    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
    æľīæĦıæĢĿ
    -0.11
    ä¸ĵå¿ĥ
    -0.10
    æĪijçļĦå¿ĥ
    -0.10
    adr
    -0.09
    ä¸ĵä¸ļçļĦ
    -0.09
    çĶŁçĶŁ
    -0.09
    ä¸į满
    -0.09
    ÑĥÑī
    -0.09
    广æĴŃçĶµè§Ĩ
    -0.09
     Tel
    -0.08
    POSITIVE LOGITS
    æĶ¾æĿ¾
    0.10
    å·²å®ĮæĪIJ
    0.10
    åºĨç¥Ŀ
    0.10
    æŀķ头
    0.10
    åĪ¶åīĤ
    0.10
    è¾īçħĮ
    0.09
    ä¼ijæģ¯
    0.09
    åĩ¼
    0.09
    åģľæ»ŀ
    0.09
    smarty
    0.09
    Activations Density 0.024%

    No Known Activations