© 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. 34697
    Prev
    Next
    INDEX
    Explanations

    reactive oxygen species (ROS)

    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
    éĢĢ
    -0.09
    ripe
    -0.09
    è¿Ī
    -0.09
    åijĪçİ°
    -0.09
     Cummings
    -0.09
    æĶĢçĻ»
    -0.09
    èļĢ
    -0.08
    åıĹå½±åĵį
    -0.08
    ä¸Ģçīĩ
    -0.08
    大å±Ģ
    -0.08
    POSITIVE LOGITS
     ROS
    0.11
    ä¸ĢåĪĢ
    0.11
    ROS
    0.10
    å··
    0.10
    9
    0.10
    姻
    0.09
    7
    0.09
    æ¶Īæ¯Ĵ
    0.09
    æŃ¼
    0.09
    5
    0.09
    Activations Density 0.319%

    No Known Activations