© 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. 37994
    Prev
    Next
    INDEX
    Explanations

    endorphin and opioid systems

    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
    æŃ»äº¡
    -0.11
     death
    -0.11
     Death
    -0.10
    death
    -0.10
    é³ŀ
    -0.09
    -death
    -0.09
    _death
    -0.09
    Death
    -0.09
    æ´»
    -0.09
     doom
    -0.09
    POSITIVE LOGITS
    æīª
    0.11
    åıijæī¬
    0.10
    åĽŀåij³
    0.09
    éĩĬ
    0.09
     Miles
    0.08
    ç¬ijèĦ¸
    0.08
     Released
    0.08
    åľ¨ç½ijä¸Ĭ
    0.08
    heimer
    0.08
    éĩĭ
    0.08
    Activations Density 0.060%

    No Known Activations