© 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. 9402
    Prev
    Next
    INDEX
    Explanations

    prone to or susceptible to

    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
    anke
    -0.10
    主æĦı
    -0.09
     trá»ĭ
    -0.09
    du
    -0.09
     retained
    -0.09
    足迹
    -0.09
    cole
    -0.09
    ä¿ĿçķĻ
    -0.09
    ResponseBody
    -0.08
    urance
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.10
    è´£
    0.10
    çĶŁäº§æĢ»åĢ¼
    0.09
    产åѦ
    0.09
    çĦ¶æĺ¯
    0.09
    orial
    0.09
    ä¹Łä¸įæĥ³
    0.08
    RON
    0.08
    責
    0.08
     Kaw
    0.08
    Activations Density 0.029%

    No Known Activations