© 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. 11432
    Prev
    Next
    INDEX
    Explanations

    running events and courses

    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
    满æĢĢ
    -0.09
    åĪłéĻ¤æĪIJåĬŁ
    -0.09
     Peaks
    -0.09
    缩水
    -0.09
     اÙĦØ´Ùĩر
    -0.09
    ä¸Ģ头
    -0.09
    æļĹæļĹ
    -0.08
    ØŃاض
    -0.08
     ventil
    -0.08
    æĸĻ
    -0.08
    POSITIVE LOGITS
    人åĬĽ
    0.10
    åľ°çĤ¹
    0.10
    çĶ¨äºº
    0.10
    èIJ¥éĢłèī¯å¥½
    0.09
    æĿ¥å®¾
    0.08
    èµ·çĤ¹
    0.08
    æľįè£ħ
    0.08
    饮æĸĻ
    0.08
    襻
    0.08
    è¯ĹæŃĮ
    0.08
    Activations Density 0.024%

    No Known Activations