© 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. 21216
    Prev
    Next
    INDEX
    Explanations

    change or change

    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
    izz
    -0.12
    ctl
    -0.10
    ChangeEvent
    -0.09
     ê°ĸ
    -0.09
     chảy
    -0.09
    åıĺæĽ´
    -0.09
    æ³ħ
    -0.09
    æĢĨ
    -0.09
    Unchecked
    -0.09
    ally
    -0.09
    POSITIVE LOGITS
    äºĨå¾Īå¤ļ
    0.12
    à¹ģà¸Ľà¸¥
    0.11
    iable
    0.11
    äºĨä»ĸçļĦ
    0.11
    主æĦı
    0.10
    åĴĮå®ĮåĸĦ
    0.10
    enate
    0.10
    iates
    0.10
    ÑģÑı
    0.09
     gì
    0.09
    Activations Density 0.074%

    No Known Activations