© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18177
    Prev
    Next
    INDEX
    Explanations

    options, futures, derivatives

    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
    ibri
    -0.10
    arya
    -0.09
    åŀ«
    -0.09
    loh
    -0.08
    ä¸į说
    -0.08
     VIA
    -0.08
    èĮ¨
    -0.08
    _plugin
    -0.08
    æ¸ł
    -0.08
     Pill
    -0.08
    POSITIVE LOGITS
    çİĭåĽ½
    0.10
    ipers
    0.09
    ASP
    0.09
    åĪ°æľŁ
    0.09
    ä¹IJæĦı
    0.09
    æĪIJé¾Ļ
    0.08
    æĸ°åĬł
    0.08
    åįģåħŃ
    0.08
    /disc
    0.08
    jsp
    0.08
    Activations Density 0.028%

    No Known Activations