© 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. 20053
    Prev
    Next
    INDEX
    Explanations

    disease and disorder

    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
    æīįæĺ¯
    -0.10
    ä¸Ģ个个
    -0.10
     же
    -0.09
    iating
    -0.09
    å¼Ħå¾Ĺ
    -0.09
    å°Ķæĸ¯
    -0.09
    ä»ħä»ħæĺ¯
    -0.09
    ä¸ĢéŨ
    -0.09
    è¿Ļæł·ä¸Ģ
    -0.09
    ä»Ģä¹Īæł·
    -0.09
    POSITIVE LOGITS
    æĹ¨åľ¨
    0.11
    çĶ±
    0.09
    .tap
    0.08
     whose
    0.08
    éĩįçĤ¹åħ³æ³¨
    0.08
    anes
    0.08
     meant
    0.08
    Menus
    0.08
    æĮĩåĩº
    0.08
    _renderer
    0.08
    Activations Density 0.475%

    No Known Activations