© 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. 61369
    Prev
    Next
    INDEX
    Explanations

    money and spending

    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
    秧
    -0.10
    lessly
    -0.09
    çľĭä¸įåĩº
    -0.09
    æį£
    -0.09
    æī¬
    -0.09
    оде
    -0.09
    æĴij
    -0.09
    ount
    -0.09
    мÑĭÑģл
    -0.09
    edor
    -0.08
    POSITIVE LOGITS
    éĴ±
    0.13
    è¶³å¤ŁçļĦ
    0.12
    åħħè£ķ
    0.10
     денег
    0.10
    æķ°é¢Ŀ
    0.10
    éĮ¢
    0.10
    æķ°çĽ®
    0.10
    è¶³å¤Ł
    0.09
     money
    0.09
     tapped
    0.09
    Activations Density 0.074%

    No Known Activations