© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8152
    Prev
    Next
    INDEX
    Explanations

    working with, continuing to, helping

    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
    æıª
    -0.09
    bolt
    -0.08
     Lager
    -0.08
    ora
    -0.08
    (AP
    -0.07
    HAL
    -0.07
    å®ĺåı¸
    -0.07
    atters
    -0.07
     DY
    -0.07
     pouch
    -0.07
    POSITIVE LOGITS
    è¿Ļæł·ä¸Ģ个
    0.13
    为广大
    0.11
    è¿Ļä¹Ī
    0.10
    è¿Ļ两天
    0.10
    精彩çļĦ
    0.10
    ä¸Ģ个æĸ°çļĦ
    0.10
    æĸ°çļĦ
    0.10
    为大家
    0.09
    å°±è¿Ļä¹Ī
    0.09
    è¿Ļä¹Ī大
    0.09
    Activations Density 0.052%

    No Known Activations