© 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. 51949
    Prev
    Next
    INDEX
    Explanations

    copyright notices and source attribution

    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
    åĨĮ
    -0.09
     Shane
    -0.09
    åIJ¹
    -0.08
    eshire
    -0.08
     bat
    -0.08
    驹
    -0.08
    åŀ¢
    -0.08
    é£İ鼨
    -0.08
     Escort
    -0.08
    çģµæĦŁ
    -0.08
    POSITIVE LOGITS
    åħľ
    0.09
    ä»ĬæĻļ
    0.09
    转载
    0.09
    æĸ°åįİ社
    0.09
    æĭ¿åĪ°
    0.09
    å±±åĿ¡
    0.08
    itor
    0.08
     Thomson
    0.08
    _EDITOR
    0.08
     editorial
    0.08
    Activations Density 0.175%

    No Known Activations