© 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. 47778
    Prev
    Next
    INDEX
    Explanations

    oxidative stress and inflammatory processes

    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
    æ½ľ
    -0.10
    éĹªçĶµ
    -0.09
    åĺ´
    -0.08
     Nev
    -0.08
     Conspiracy
    -0.08
    éĤ£è¾¹
    -0.08
    ephy
    -0.08
    expects
    -0.08
     nap
    -0.08
    çĹķ
    -0.08
    POSITIVE LOGITS
    è¿ĩå¤ļ
    0.12
    æľī害
    0.11
    éħ¿
    0.10
     AGE
    0.09
    ROS
    0.09
    AGES
    0.09
    æįŁä¼¤
    0.09
     STREET
    0.09
    å¢ŀé«ĺ
    0.09
     ageing
    0.09
    Activations Density 0.742%

    No Known Activations