© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23987
    Prev
    Next
    INDEX
    Explanations

    finance and tax terms

    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
    lux
    -0.09
    ä¸Ģç«Ļ
    -0.09
    ãģĮãĤī
    -0.09
    beat
    -0.08
    主åĬĽ
    -0.08
     Deposit
    -0.08
    ä¸ī代
    -0.08
    ï¾ŀ
    -0.08
    ils
    -0.08
    Indent
    -0.08
    POSITIVE LOGITS
    è°ĵ
    0.09
    åľºé¦Ĩ
    0.09
    çĭ¬
    0.09
    å¼łåħĪçĶŁ
    0.09
    å¤ĸåľ°
    0.09
    éģĹ
    0.09
    æĬĢå¸Ī
    0.09
    çħŀ
    0.09
    åIJ¬å¾Ĺ
    0.09
    èĻ
    0.08
    Activations Density 0.072%

    No Known Activations