© 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. 10784
    Prev
    Next
    INDEX
    Explanations

    health insurance benefits

    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
    ÑĩаÑĤ
    -0.14
    妯
    -0.11
    à¹Ĥ
    -0.09
    å¿ĥåºķ
    -0.09
    Injector
    -0.09
    é¡
    -0.08
    æĹłå£°
    -0.08
    éªŀ
    -0.08
    åĵ²
    -0.08
    oday
    -0.08
    POSITIVE LOGITS
    å¾ħéģĩ
    0.12
    ç¦ıåĪ©
    0.11
    社ä¼ļä¿ĿéĻ©
    0.11
    社ä¼ļä¿Ŀéļľ
    0.10
    ä¸įå¾Ĺ
    0.09
    æĬ¥éħ¬
    0.09
    æŃ£è§Ħ
    0.09
    æĿĥçĽĬ
    0.09
    urance
    0.08
    æĸĹ
    0.08
    Activations Density 0.061%

    No Known Activations