© 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. 19258
    Prev
    Next
    INDEX
    Explanations

    financial instruments and treasuries

    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
    åľ¨æ¸¸æĪıä¸Ń
    -0.11
    æĻļä¸Ĭ
    -0.10
    æ¡ģ
    -0.09
    ä¸įæĺİ
    -0.09
    é£ŀè·ĥ
    -0.09
    ä¸Ĭ课
    -0.09
    åĪłéĻ¤æĪIJåĬŁ
    -0.09
    ç«ŀæĬĢ
    -0.09
    æģ¶å¿ĥ
    -0.09
    _SIM
    -0.09
    POSITIVE LOGITS
    åĽ½åĢº
    0.12
    åĢºåĪ¸
    0.09
    éĩijçīĮ
    0.08
    idy
    0.08
    indexed
    0.08
    纳æĸ¯
    0.08
    sto
    0.08
    æĥ°
    0.08
    çijļ
    0.08
     Mog
    0.08
    Activations Density 0.020%

    No Known Activations