© 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. 54664
    Prev
    Next
    INDEX
    Explanations

    IRS tax returns

    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
    å®ŀåĬĽ
    -0.09
    å¼ķæµģ
    -0.09
    æ³ķåħ°
    -0.09
     Stamford
    -0.09
    æĬ¼éĩij
    -0.08
    åºł
    -0.08
    奢
    -0.08
     Observer
    -0.08
    è§Ģå¯Ł
    -0.08
    è§Ĥå¯Ł
    -0.08
    POSITIVE LOGITS
    IRS
    0.11
     IRS
    0.09
    åŃ£
    0.09
    å¨ĺ
    0.09
    aison
    0.08
    æĸ°æĺ¥
    0.08
    æĬĬèĩªå·±çļĦ
    0.08
    aptcha
    0.08
    afs
    0.08
    æĺ¥èĬĤ
    0.08
    Activations Density 0.096%

    No Known Activations