© 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. 53054
    Prev
    Next
    INDEX
    Explanations

    insect pursuit

    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
    人群
    -0.09
    èĬ¦
    -0.09
    è°£è¨Ģ
    -0.09
    èĢģèĻİ
    -0.08
    çªģåıijäºĭ件
    -0.08
    ÑĤоп
    -0.08
    éĢīæĭ
    -0.08
    é©´
    -0.08
    çĭ®åŃIJ
    -0.08
    ç»ıèIJ¥æ´»åĬ¨
    -0.08
    POSITIVE LOGITS
     ÑģпеÑĨиалÑĮно
    0.10
    åĬĪ
    0.08
    æıIJä¾ĽçļĦ
    0.08
    æ®ĭ
    0.08
     пÑĢедоÑģÑĤавлен
    0.08
    为åħ¶
    0.08
    ç¢İçīĩ
    0.08
    moth
    0.08
    æīĢæıIJä¾ĽçļĦ
    0.08
    ìłľ
    0.08
    Activations Density 0.117%

    No Known Activations