© 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. 54637
    Prev
    Next
    INDEX
    Explanations

    income and revenue sources

    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
    èĮķ
    -0.09
    è°¨æħİ
    -0.09
    èĤ¤
    -0.09
    ä¼łè¾¾
    -0.09
    窿
    -0.08
    çĽ¸äº²
    -0.08
    inton
    -0.08
     thái
    -0.08
    åı®
    -0.08
    åıĹ害èĢħ
    -0.08
    POSITIVE LOGITS
    æĶ¶åħ¥
    0.19
     income
    0.15
     sources
    0.13
     revenue
    0.12
    æĿ¥æºIJ
    0.12
    æĢ»æĶ¶åħ¥
    0.12
    income
    0.12
     Income
    0.11
     Sources
    0.11
    Sources
    0.11
    Activations Density 0.047%

    No Known Activations