© 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. 53105
    Prev
    Next
    INDEX
    Explanations

    video playback requirements

    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
    åıĺæĢģ
    -0.09
    éĤ£ä¹Īå¤ļ
    -0.08
    管家
    -0.08
    .Library
    -0.08
    éľĪ
    -0.08
     Sant
    -0.08
    äºļåĨĽ
    -0.08
     trùng
    -0.08
    /Typography
    -0.08
    æĺ¯è°ģ
    -0.08
    POSITIVE LOGITS
    æĮª
    0.09
     Goat
    0.09
    éĻĢ
    0.09
     improv
    0.08
    aho
    0.08
    Ñıз
    0.08
    ä¸įåıĹ
    0.08
    íĥĪ
    0.08
    为äºĨ让
    0.08
    çī¢çī¢
    0.08
    Activations Density 0.055%

    No Known Activations