© 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. 38576
    Prev
    Next
    INDEX
    Explanations

    fatty acids metabolism

    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
    æ»ļ
    -0.09
    æ¶ĪåĮĸ
    -0.09
    ä¿¡ä»°
    -0.09
    èİ·å¾ĹæĦŁ
    -0.09
    ç»Ī身
    -0.09
     BASIS
    -0.09
    iton
    -0.08
    æķ´ä¸ªäºº
    -0.08
    çĨı
    -0.08
    gravity
    -0.08
    POSITIVE LOGITS
    æķıéĶIJ
    0.09
    æĭ¬
    0.09
    ä¸Ĭ游
    0.08
    å½ķåĪ¶
    0.08
    ANO
    0.08
    abant
    0.08
    IndexChanged
    0.08
    æ²½
    0.08
    FORMATION
    0.08
    çIJ®
    0.08
    Activations Density 0.442%

    No Known Activations