© 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. 33331
    Prev
    Next
    INDEX
    Explanations

    money, payment, or wages

    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
    æĢ»æĺ¯
    -0.10
    èĭ´
    -0.09
    .sponge
    -0.09
    æķ¬
    -0.09
    總æĺ¯
    -0.09
    积
    -0.09
    游æĪıä¸Ń
    -0.08
    æĦıè¯Ĩ
    -0.08
    æĴŀ
    -0.08
    евиÑĩ
    -0.08
    POSITIVE LOGITS
    äºī夺
    0.08
    æįįåį«
    0.08
    åį«
    0.08
    æľ¬èĥ½
    0.08
     lay
    0.08
    lay
    0.08
    ØŃصÙĪÙĦ
    0.08
    驱
    0.08
     Lay
    0.08
    éĿĵ
    0.08
    Activations Density 0.054%

    No Known Activations