© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    thank you

    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
     fixtures
    -0.09
    踵
    -0.09
    åIJģ
    -0.09
    éĢĨ
    -0.09
     Constit
    -0.09
    大çĽĺ
    -0.09
    æľīèĩªå·±çļĦ
    -0.09
    åĩºæĿ¥äºĨ
    -0.09
    ä¼ĺäºİ
    -0.08
     ÑĨелÑĮÑİ
    -0.08
    POSITIVE LOGITS
    æĻ¯å¾·
    0.09
    表åĨ³
    0.09
    çĭ¬
    0.08
    mall
    0.08
    æĮĩçĤ¹
    0.08
    rieve
    0.08
    çļĦçģµéŃĤ
    0.08
    ç°§
    0.08
    çļĦ帮åĬ©
    0.08
    èµĦæĸĻ
    0.08
    Activations Density 0.025%

    No Known Activations