© 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. 62312
    Prev
    Next
    INDEX
    Explanations

    live online meetings and webinars

    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
    åħ¨éĿ¢èIJ½å®ŀ
    -0.10
    å§Ķæīĺ
    -0.10
    æĬ¥çº¸
    -0.09
    ç¼´
    -0.09
    /LICENSE
    -0.09
     Tiên
    -0.08
    è
    -0.08
    eson
    -0.08
    驾驶è¯ģ
    -0.08
    å¥ij
    -0.08
    POSITIVE LOGITS
    缴æĴŃ
    0.16
    缴æĴŃéĹ´
    0.15
    主æĴŃ
    0.13
    å±ĬæŶ
    0.12
    çŃĶçĸij
    0.11
    主æĮģ人
    0.11
    åľ¨çº¿
    0.11
    äºij端
    0.11
    åĩĨæŶ
    0.10
     webinar
    0.10
    Activations Density 0.040%

    No Known Activations