© 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. 21248
    Prev
    Next
    INDEX
    Explanations

    begun or started

    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
    iage
    -0.10
    çĤ¯
    -0.10
    ç»ıéªĮ丰å¯Į
    -0.09
    è¿ĩæĿ¥
    -0.09
    elu
    -0.09
    éªĭ
    -0.09
    æĻ¯å¾·
    -0.09
    ify
    -0.09
    åħ·æľīèī¯å¥½
    -0.09
    TRS
    -0.08
    POSITIVE LOGITS
    å¼ĢæĪ·
    0.11
    ç½
    0.11
    енно
    0.10
    å¼Ģè¾Ł
    0.09
    å°ļ书
    0.09
    ofile
    0.09
    cil
    0.08
    çĶľèľľ
    0.08
    åĬ¨å·¥
    0.08
    æĽ¿ä»£
    0.08
    Activations Density 0.021%

    No Known Activations