© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19509
    Prev
    Next
    INDEX
    Explanations

    credit default and loans

    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
    exc
    -0.10
    æij¸
    -0.09
    å®Ĺ
    -0.09
    é¾Ł
    -0.09
    æĸ¤
    -0.09
    æ£Ģå¯Łæľºåħ³
    -0.09
    uffle
    -0.09
     excited
    -0.09
    èĥĸ
    -0.09
    -Clause
    -0.09
    POSITIVE LOGITS
    (AT
    0.09
    æ±ĩ
    0.08
    贷款
    0.08
     Morg
    0.08
     Dish
    0.08
    æĵ¢
    0.08
    飶
    0.08
    æľ¬çĿĢ
    0.08
    iers
    0.08
    æįŁå¤±
    0.08
    Activations Density 0.127%

    No Known Activations